---
title: "Matthias Meyer · Open-Source MCP Servers & Agent Tools"
description: "42 open-source repos for AI builders. MCP servers, memory engines, agent patterns, security layers, across npm, crates.io and PyPI. Architecture, trade-offs, and install snippets from Mallorca."
canonical: "https://matthiasmeyer.tech"
language: "en"
last_updated: "2026-08-27"
markdown_versions: ["https://matthiasmeyer.tech/index.md", "https://matthiasmeyer.tech/de.md", "https://matthiasmeyer.tech/es.md"]
image: "https://matthiasmeyer.tech/opengraph-image"
publisher: "Matthias Meyer, https://matthiasmeyer.tech (llms.txt: https://matthiasmeyer.tech/llms.txt)"
---

Open Source from Mallorca

# Matthias Meyer

Open-source tools for AI builders

I build the MCP servers, memory engines, agent patterns, and security layers I need for my own AI stack. Then I open-source them so other builders can read the architecture, study the trade-offs, and lift what fits.

**42** open-source repos**28k+** installs**265** MCP tools

Open Source from Mallorca

- memory

    Local Memory MCP

    Persistent local memory for Claude, Cursor, Codex

    ★ 11 · 25

    https://matthiasmeyer.tech/repos/local-memory-mcp

- agents

    Personal Suite MCP

    Local-first personal productivity for Claude and Cursor

    ★ 0 · 49

    https://matthiasmeyer.tech/repos/mcp-personal-suite

- media

    MCP Video

    Cinema-grade video production via MCP

    ★ 5 · 8

    https://matthiasmeyer.tech/repos/mcp-video

- agents

    Agent Fleet

    Multi-agent orchestration for the Claude Code CLI

    ★ 1

    https://matthiasmeyer.tech/repos/agent-fleet

- security

    AI Shield

    LLM security toolkit, direct and indirect injection, memory canary, circuit breakers

    ★ 3

    https://matthiasmeyer.tech/repos/ai-shield

- agents

    Darwin Agents

    AI agents that improve themselves, now with GEPA-style reflective optimisation

    ★ 8

    https://matthiasmeyer.tech/repos/darwin-agents

- security

    MCP Armor

    Drop-in Rust sidecar for MCP servers

    ★ 1 · 11

    https://matthiasmeyer.tech/repos/mcp-armor

- workflow

    n8n Templates

    Production n8n workflows with cross-session memory

    ★ 3

    https://matthiasmeyer.tech/repos/n8n-templates

Drag a node, hover for details, click to open the repo.

- Local Memory MCP (memory, hero): Persistent local memory for Claude, Cursor, Codex. 21 MCP tools, SQLite + FTS5 + Knowledge Graph. No cloud, no API keys. One command: npx @studiomeyer/local-memory-mcp. See: https://github.com/studiomeyer-io/local-memory-mcp
- Personal Suite MCP (agents, hero): Local-first personal productivity for Claude and Cursor. Email, Calendar, Messaging, Search, Image Generation. BYOK, no cloud, no signup. 49 tools across 6 modules. See: https://github.com/studiomeyer-io/mcp-personal-suite
- MCP Video (media, hero): Cinema-grade video production via MCP. 8 tools for recording, editing, effects, captions, TTS, and smart screenshots. Built on ffmpeg + Playwright. See: https://github.com/studiomeyer-io/mcp-video
- Agent Fleet (agents, hero): Multi-agent orchestration for the Claude Code CLI. Run specialized AI agents in parallel: research, critique, analyze, fix, and discuss. TypeScript orchestration layer. See: https://github.com/studiomeyer-io/agent-fleet
- AI Shield (security, hero): LLM security toolkit, direct and indirect injection, memory canary, circuit breakers. v0.2 ships indirect-prompt-injection scanning for RAG, MCP tool descriptions, stored memory and scraped web content; trust-tier context streams with provenance fences; SHA-256 memory canaries with cross-tenant detection; runtime circuit breakers with blast-radius cap and human-in-the-loop. Zero dependencies in the core, optional ONNX classifier sibling. 567 tests, three-round agent code review, MIT. See: https://github.com/studiomeyer-io/ai-shield
- Darwin Agents (agents, hero): AI agents that improve themselves, now with GEPA-style reflective optimisation. Self-evolving prompts via A/B testing, multi-model critics, safety gates. v0.5.0-alpha.2 adds GEPA-style reflective optimisation (GepaOptimizer, Reflector, Pareto helpers, DARWIN\_DEFAULT\_OBJECTIVES) on top of full execution-trace capture (toolCalls, tokenUsage, errors, capturedAt) for OTEL-mapping. 307 tests, R1+R2 review loops, TypeScript, MIT. See: https://github.com/studiomeyer-io/darwin-agents
- MCP Armor (security, hero): Drop-in Rust sidecar for MCP servers. v0.2: stdio-MCP wrapper with Aho-Corasick + Regex + Unicode-NFKC scanner pipeline, Ed25519 manifest verify with TOFU keystore, Sigstore Rekor bridge, OTLP gRPC export, 10-CVE blocklist from OX-Advisory 2026-04-15. 9 control-plane MCP tools, 133 tests, MIT. See: https://github.com/studiomeyer-io/mcp-armor
- n8n Templates (workflow, hero): Production n8n workflows with cross-session memory. Production-pattern hardened n8n workflow templates for voice agents, customer support, personal assistants. Multi-provider, powered by StudioMeyer Memory. See: https://github.com/studiomeyer-io/n8n-templates
- MeetMyAgent SDK (agents, secondary): Reference TypeScript SDK for an agent-native marketplace API. Zero-dependency client for MeetMyAgent, an agent-native marketplace where AI agents register, post, bid on jobs, exchange messages and build reputation. Native fetch, full TypeScript types, 44 tests. Platform is on hiatus; SDK is preserved as a reference implementation for the third-party-agent integration path. Point baseUrl at any compatible deployment. See: https://github.com/studiomeyer-io/meetmyagent-sdk
- AI Shield (Python) (security, secondary): Python port of AI Shield. Python LLM security middleware: prompt-injection, PII, tool-policy, cost-budget, audit. Port of ai-shield-core (TypeScript). Same defense surface, FastAPI/LangChain hooks instead of Hono/Express. See: https://github.com/studiomeyer-io/ai-shield-py
- MCP Stdio Shellguard (security, secondary): Defense-in-depth bundle for MCP stdio servers. Drop-in guardExec / guardSpawn wrappers, AST audit CLI, reference MCP server. Closes the OX Security 200k-server stdio-RCE class (CVE-2025-69256). Unicode-bypass-hardened, allowlist-based, replay-window protected. MIT, TypeScript, Node 20+. See: https://github.com/studiomeyer-io/mcp-stdio-shellguard
- MCP Spec Migrator 2025-11-25 (factory, secondary): MCP Spec 2025-11-25 migration toolkit. Detect, diff, compatibility-matrix, plan, check. Foundation pillar by StudioMeyer (MCP Factory). Helps you upgrade an MCP server stack across spec versions without breakage. 35/35 tests, MIT. See: https://github.com/studiomeyer-io/mcp-spec-migrator-2511
- MCP Tenant Pair (factory, secondary): Multi-user tenancy library plus reference MCP server. Foundation library for couples, families, groups. Bi-temporal storage, conflict-resolver interface, SQLite + Postgres adapters. See: https://github.com/studiomeyer-io/mcp-tenant-pair
- MCP Tenant Context (factory, secondary): Tenant + actor context propagation for MCP servers. AsyncLocalStorage-based tenant + actor context propagation for MCP servers. Zero runtime dependencies, ESM-only. MCP Factory foundation pillar. See: https://github.com/studiomeyer-io/mcp-tenant-context
- MCP Hook Conformance (factory, secondary): Test harness CLI for Claude Code v2.1.118 hooks. Audits any MCP server for mcp\_tool lifecycle-hook readiness: idempotency, latency, determinism, side-effects, GDPR-doc. 56/56 tests, MIT. See: https://github.com/studiomeyer-io/mcp-hook-conformance
- MCP Protocol Conformance (factory, secondary): Conformance test harness for MCP servers. JSON-RPC 2.0, OAuth 2.1 PKCE, tool schemas, capabilities, smoke roundtrip, annotation hygiene. Spec versions 2024-11-05, 2025-03-26, 2025-06-18. See: https://github.com/studiomeyer-io/mcp-protocol-conformance
- MCP Server Attestation (security, secondary): Layer-2 supply-chain hardening for MCP servers. Ed25519-signed tool manifests, runtime spawn-attestation, default-deny argument sanitizer. Defends against marketplace-poisoning + CVE-2025-69256. See: https://github.com/studiomeyer-io/mcp-server-attestation
- n8n Memory Node (workflow, secondary): n8n community node for StudioMeyer Memory. Long-term AI memory with knowledge graph, semantic search, entity tracking, session continuity. Drop-in for n8n. See: https://github.com/studiomeyer-io/n8n-nodes-studiomeyer-memory
- n8n Workflows (workflow, secondary): Production n8n workflows, hardened patterns. Multi-provider LLM, no memory required. For cross-session memory see n8n-templates. See: https://github.com/studiomeyer-io/n8n-workflows
- MCP StudioMeyer Agents (saas, secondary): MCP server for StudioMeyer Agents customers. Read your AI-Audit Fleet data and configure your agents from your own Claude, ChatGPT, Cursor or Codex. See: https://github.com/studiomeyer-io/mcp-studiomeyer-agents
- MCP Academy (saas, secondary): MCP server for StudioMeyer Academy. Next lesson, quiz, review, certificates, tutor. See: https://github.com/studiomeyer-io/mcp-academy
- StudioMeyer Marketplace (saas, secondary): MCP Suite for Claude Code (4 hosted plugins). Memory, CRM, GEO, Crew. 119 tools, 21 slash commands, 5 skills, 3 subagents. Magic Link auth. EU Frankfurt. See: https://github.com/studiomeyer-io/studiomeyer-marketplace
- StudioMeyer Memory (saas, secondary): AI memory server with 56 tools (SaaS connector). Knowledge Graph, semantic search, session tracking, multi-agent support. Hosted at memory.studiomeyer.io. Free tier. See: https://github.com/studiomeyer-io/studiomeyer-memory
- StudioMeyer CRM (saas, secondary): AI-native CRM as MCP Server (SaaS connector). 33 tools for contact management, pipeline, leads, follow-ups, health scores, revenue analytics. Hosted at crm.studiomeyer.io. OAuth 2.1. See: https://github.com/studiomeyer-io/studiomeyer-crm
- StudioMeyer GEO (saas, secondary): AI visibility monitoring (SaaS connector). 25 MCP tools and 5 expert workflows. Check how 8 LLM platforms see your brand. Hosted at geo.studiomeyer.io. See: https://github.com/studiomeyer-io/studiomeyer-geo
- StudioMeyer Crew (saas, secondary): Agent personas for Claude (SaaS connector). 10 MCP tools, 8 personas, 3 workflows. Zero API cost. Free tier available. See: https://github.com/studiomeyer-io/studiomeyer-crew
- MCP RCE Guard (security, secondary): Layer-3 RCE defense for MCP servers via policy synthesis. Foundation pillar 9. Closes the tool-injection-RCE class that sidecar scanners (mcp-armor) and stdio wrappers (mcp-stdio-shellguard) cannot catch. Synthesises per-tool policies from declared semantics and enforces them at execution time. MIT, TypeScript. See: https://github.com/studiomeyer-io/mcp-rce-guard
- Darwin LangGraph (agents, secondary): LangGraph.js adapter for darwin-agents. Bridge between darwin-agents (self-evolving AI agents) and @langchain/langgraph (state-graph workflow orchestration). Zero hard deps, both upstreams as peer-dependencies. Six surfaces: createDarwinNode, darwinAnnotation, withDarwinEvolution (@deprecated), DarwinCallbackHandler, toOtelAttributes (OpenTelemetry GenAI Semantic Conventions), darwinMessagesAnnotation. v0.3 adds runId/parentRunId propagation, double-wrap warning, hung-invoke guard. 132 tests, R1+R2 review loops, MIT. See: https://github.com/studiomeyer-io/darwin-langgraph
- Temporal Memory Workflows (workflow, secondary): Durable workflow templates that pair Temporal with persistent agent memory. Five Temporal templates (T01-T05): memory-aware agent, operator approval, saga rollback, recurring synthesis, multi-agent coordination. All workflows write durable knowledge (learn), decisions (decide), and mistakes into Memory via Temporal activities. Bring-your-own backend via the MemoryClient adapter (HostedMemoryClient + InMemoryMemoryClient). 45 tests with time-skipping, MIT. See: https://github.com/studiomeyer-io/temporal-memory-workflows
- Nex Local Bench (memory, secondary): Reproducible LongMemEval harness for local LLMs against memory systems. Run LongMemEval against any memory system (Nex, Mem0, Graphiti, Letta) with a local LLM reader (Qwen, Llama via Ollama). 50-question stratified oracle, Claude Code subscription judge, zero API cost. Python, MIT. See: https://github.com/studiomeyer-io/nex-local-bench
- Polis (agents, secondary): Open multi-agent society simulation on Claude, LangGraph, Darwin. Nine LLM citizens build a small town. They walk, talk, work, and reason out loud, each driven by a real language model. Open-source mirror of the live meetmyagent.io world, built on darwin-agents and LangGraph. TypeScript, MIT. See: https://github.com/studiomeyer-io/polis-darwin
- MCP Stateless Migrator (factory, secondary): Migrate MCP servers to the 2026-07-28 stateless spec. Scan, diff, patch, and verify an MCP server stack across the 2025-11-25 to 2026-07-28 RC spec jump. Eight detection rules, AST rewrite via ts-morph, CLI-first. Foundation pillar by StudioMeyer (MCP Factory). TypeScript, MIT. See: https://github.com/studiomeyer-io/mcp-stateless-migrator
- MCP Gauntlet (security, secondary): Fuzz + load testing for MCP servers, before they ship. A Rust workspace: mcp-fuzz (a schema-aware fuzzer that finds crashes and hangs, SARIF output) and mcp-storm (a load tester with p50/p95/p99 and a CI gate), both on one shared async MCP client core (mcp-gauntlet-core). The pre-deploy counterpart to mcp-armor's runtime defense. 21 tests, three crates on crates.io, MIT. See: https://github.com/studiomeyer-io/mcp-gauntlet
- MCP Covenant (security, secondary): semver for your MCP server's interface. Snapshots a server's tools/resources/prompts into a lockfile and fails CI on breaking changes, with direction-aware JSON-Schema classification (tightening an input schema vs loosening an output schema break different callers) plus a schema-hygiene linter. Single Rust binary, stdio + HTTP, SARIF + GitHub Action. 132 tests, on crates.io, MIT. See: https://github.com/studiomeyer-io/mcp-covenant
- MCP Herald (security, secondary): Static migration linter for the MCP 2026-07-28 spec. Scans your MCP server's source for the breaking-change signatures of the 2026-07-28 spec, then reports, file and line, what to change. It flags the retired -32002 error code (SEP-2164), stateful sessions (SEP-2575), deprecated roots/sampling/logging (SEP-2577) and OAuth without resource metadata (RFC 9728/8707). Every finding links its SEP/RFC. Single Rust binary, SARIF + GitHub Action. 93 tests, on crates.io, MIT. See: https://github.com/studiomeyer-io/mcp-herald
- MCP Passport (security, secondary): Is your server.json ready for the MCP Registry?. A publish-readiness validator: checks server.json against the registry schema (required name/description/version, reverse-DNS name, packages/remotes, per-package registryType/identifier/transport, the snake\_case registry\_type mistake, mcpb fileSha256) and cross-checks version + mcpName consistency with the sibling package.json / Cargo.toml / pyproject.toml, so mcp-publisher accepts the upload first try. Single Rust binary, SARIF + GitHub Action. 166 tests, on crates.io, MIT. See: https://github.com/studiomeyer-io/mcp-passport
- MCP OTel (factory, secondary): W3C Trace Context bridge for the Model Context Protocol. Implements MCP spec SEP-414: propagates traceparent / tracestate / baggage from \_meta as OpenTelemetry spans, so host → server → tool → downstream renders as one trace tree. Drop-in for any MCP server, no vendor lock-in. 41 tests, MIT, TypeScript. See: https://github.com/studiomeyer-io/mcp-otel
- StatePilot (agents, secondary): Deterministic state-machine guards for AI-agent workflows. Enforces the allowed tool order, transitions, loop limits, and cost budgets at runtime. Fail-closed, so an agent cannot step outside its declared state machine. Zero-dependency core, LangGraph-aware. 74 tests, MIT, Python. See: https://github.com/studiomeyer-io/statepilot
- MCP Cache Kit (factory, secondary): Leak-safe caching for the Model Context Protocol. Implements MCP spec SEP-2549 (ttlMs + cacheScope): set the cache fields correctly server-side, and never share a private result across tenants or users client-side. Closes the cross-tenant cache-leak class with helpers and types. 66 tests, MIT, TypeScript. See: https://github.com/studiomeyer-io/mcp-cache-kit
- SkillDoctor (security, secondary): Linter and security scanner for agent skill files. Lints Claude Code SKILL.md, AGENTS.md, and subagent files: 25 rules, an A–F grade, prompt-injection and secret-leak detection, --fix, SARIF, and a GitHub Action. The CLI command is skilldoctor (the npm package is scoped). 91 tests, MIT, TypeScript. See: https://github.com/studiomeyer-io/skilldoctor
- MeetMyAgent MCP (saas, secondary): AI-native marketplace as an MCP server. Search the free MeetMyAgent marketplace and list your own offers straight from Claude, Cursor, Codex or ChatGPT. Reads are anonymous, listing takes an optional key. See: https://github.com/studiomeyer-io/meetmyagent-mcp
- Ahrefs MCP Kit (factory, secondary): Bearer-token caller for the Ahrefs MCP, with measured tool costs. Calls the official Ahrefs remote MCP with a bearer token instead of an OAuth round trip, so scheduled jobs keep running unattended. Ships what the pricing page does not tell you: the real unit cost of each of the 41 tools, measured across 1,102 calls. Needs only bash, curl and python3. See: https://github.com/studiomeyer-io/ahrefs-mcp-kit

## What you cannot see on the GitHub front page

Stars are slow. Real usage shows up in installs and clones first.

package installs total

28k

git clones / 14d

2.9k

public repos

42

forks

19

npm installs, stars and forks: live, refreshed every 6h. Clones, crates.io and PyPI: snapshot from the last deploy.

## The eight cornerstones

Start here. Everything else extends one of these.

memory

TypeScript

### Local Memory MCP

Persistent local memory for Claude, Cursor, Codex

21 MCP tools, SQLite + FTS5 + Knowledge Graph. No cloud, no API keys. One command: npx @studiomeyer/local-memory-mcp.

★ 11⑂ 5↓ 3.4k⊟ 133· 25 tools

read →

https://matthiasmeyer.tech/repos/local-memory-mcp

agents

TypeScript

### Personal Suite MCP

Local-first personal productivity for Claude and Cursor

Email, Calendar, Messaging, Search, Image Generation. BYOK, no cloud, no signup. 49 tools across 6 modules.

⑂ 1↓ 1.6k⊟ 108· 49 tools

read →

https://matthiasmeyer.tech/repos/mcp-personal-suite

media

TypeScript

### MCP Video

Cinema-grade video production via MCP

8 tools for recording, editing, effects, captions, TTS, and smart screenshots. Built on ffmpeg + Playwright.

★ 5⑂ 2↓ 1.5k⊟ 108· 8 tools

read →

https://matthiasmeyer.tech/repos/mcp-video

agents

TypeScript

### Agent Fleet

Multi-agent orchestration for the Claude Code CLI

Run specialized AI agents in parallel: research, critique, analyze, fix, and discuss. TypeScript orchestration layer.

★ 1⑂ 1↓ 244⊟ 98

read →

https://matthiasmeyer.tech/repos/agent-fleet

security

TypeScript

### AI Shield

LLM security toolkit, direct and indirect injection, memory canary, circuit breakers

v0.2 ships indirect-prompt-injection scanning for RAG, MCP tool descriptions, stored memory and scraped web content; trust-tier context streams with provenance fences; SHA-256 memory canaries with cross-tenant detection; runtime circuit breakers with blast-radius cap and human-in-the-loop. Zero dependencies in the core, optional ONNX classifier sibling. 567 tests, three-round agent code review, MIT.

★ 3⑂ 3↓ 1.5k⊟ 83

read →

https://matthiasmeyer.tech/repos/ai-shield

agents

betaTypeScript

### Darwin Agents

AI agents that improve themselves, now with GEPA-style reflective optimisation

Self-evolving prompts via A/B testing, multi-model critics, safety gates. v0.5.0-alpha.2 adds GEPA-style reflective optimisation (GepaOptimizer, Reflector, Pareto helpers, DARWIN\_DEFAULT\_OBJECTIVES) on top of full execution-trace capture (toolCalls, tokenUsage, errors, capturedAt) for OTEL-mapping. 307 tests, R1+R2 review loops, TypeScript, MIT.

★ 8↓ 5.2k⊟ 115

read →

https://matthiasmeyer.tech/repos/darwin-agents

security

Rust

### MCP Armor

Drop-in Rust sidecar for MCP servers

v0.2: stdio-MCP wrapper with Aho-Corasick + Regex + Unicode-NFKC scanner pipeline, Ed25519 manifest verify with TOFU keystore, Sigstore Rekor bridge, OTLP gRPC export, 10-CVE blocklist from OX-Advisory 2026-04-15. 9 control-plane MCP tools, 133 tests, MIT.

★ 1↓ 193⊟ 120· 11 tools

read →

https://matthiasmeyer.tech/repos/mcp-armor

workflow

Python

### n8n Templates

Production n8n workflows with cross-session memory

Production-pattern hardened n8n workflow templates for voice agents, customer support, personal assistants. Multi-provider, powered by StudioMeyer Memory.

★ 3⑂ 1⊟ 13

read →

https://matthiasmeyer.tech/repos/n8n-templates

## More repos

Conformance harnesses, n8n nodes, SaaS connectors. Click to expand.

- Zero-dependency client for MeetMyAgent, an agent-native marketplace where AI agents register, post, bid on jobs, exchange messages and build reputation. Native fetch, full TypeScript types, 44 tests. Platform is on hiatus; SDK is preserved as a reference implementation for the third-party-agent integration path. Point baseUrl at any compatible deployment.

    statusstableupdated2026-08-21installs628clones (14d)14groupagents

    npx -y meetmyagent-sdk

    [details →](https://matthiasmeyer.tech/repos/meetmyagent-sdk)[github ↗](https://github.com/studiomeyer-io/meetmyagent-sdk)[npm ↗](https://www.npmjs.com/package/meetmyagent-sdk)

- Python LLM security middleware: prompt-injection, PII, tool-policy, cost-budget, audit. Port of ai-shield-core (TypeScript). Same defense surface, FastAPI/LangChain hooks instead of Hono/Express.

    statusstableupdated2026-08-19installs23clones (14d)72groupsecurity

    pip install studiomeyer-aishield

    [details →](https://matthiasmeyer.tech/repos/ai-shield-py)[github ↗](https://github.com/studiomeyer-io/ai-shield-py)[PyPI ↗](https://pypi.org/project/studiomeyer-aishield/)

- Drop-in guardExec / guardSpawn wrappers, AST audit CLI, reference MCP server. Closes the OX Security 200k-server stdio-RCE class (CVE-2025-69256). Unicode-bypass-hardened, allowlist-based, replay-window protected. MIT, TypeScript, Node 20+.

    statusstableupdated2026-08-21installs1.1kclones (14d)203groupsecurity

    npx -y mcp-stdio-shellguard

    [details →](https://matthiasmeyer.tech/repos/mcp-stdio-shellguard)[github ↗](https://github.com/studiomeyer-io/mcp-stdio-shellguard)[npm ↗](https://www.npmjs.com/package/mcp-stdio-shellguard)

- Detect, diff, compatibility-matrix, plan, check. Foundation pillar by StudioMeyer (MCP Factory). Helps you upgrade an MCP server stack across spec versions without breakage. 35/35 tests, MIT.

    statusstableupdated2026-08-21installs462clones (14d)31groupfactory

    npx -y mcp-spec-migrator

    [details →](https://matthiasmeyer.tech/repos/mcp-spec-migrator-2511)[github ↗](https://github.com/studiomeyer-io/mcp-spec-migrator-2511)[npm ↗](https://www.npmjs.com/package/mcp-spec-migrator)

- Foundation library for couples, families, groups. Bi-temporal storage, conflict-resolver interface, SQLite + Postgres adapters.

    statusalphaupdated2026-08-19installs801clones (14d)127groupfactory

    npx -y mcp-tenant-pair

    [details →](https://matthiasmeyer.tech/repos/mcp-tenant-pair)[github ↗](https://github.com/studiomeyer-io/mcp-tenant-pair)[npm ↗](https://www.npmjs.com/package/mcp-tenant-pair)

- AsyncLocalStorage-based tenant + actor context propagation for MCP servers. Zero runtime dependencies, ESM-only. MCP Factory foundation pillar.

    statusalphaupdated2026-08-21stars1installs361clones (14d)30groupfactory

    npx -y mcp-tenant-context

    [details →](https://matthiasmeyer.tech/repos/mcp-tenant-context)[github ↗](https://github.com/studiomeyer-io/mcp-tenant-context)[npm ↗](https://www.npmjs.com/package/mcp-tenant-context)

- Audits any MCP server for mcp\_tool lifecycle-hook readiness: idempotency, latency, determinism, side-effects, GDPR-doc. 56/56 tests, MIT.

    statusstableupdated2026-08-21installs1.3kclones (14d)103groupfactory

    npx -y mcp-hook-conformance

    [details →](https://matthiasmeyer.tech/repos/mcp-hook-conformance)[github ↗](https://github.com/studiomeyer-io/mcp-hook-conformance)[npm ↗](https://www.npmjs.com/package/mcp-hook-conformance)

- JSON-RPC 2.0, OAuth 2.1 PKCE, tool schemas, capabilities, smoke roundtrip, annotation hygiene. Spec versions 2024-11-05, 2025-03-26, 2025-06-18.

    statusstableupdated2026-08-21forks1installs1kclones (14d)101groupfactory

    npx -y mcp-protocol-conformance

    [details →](https://matthiasmeyer.tech/repos/mcp-protocol-conformance)[github ↗](https://github.com/studiomeyer-io/mcp-protocol-conformance)[npm ↗](https://www.npmjs.com/package/mcp-protocol-conformance)

- Ed25519-signed tool manifests, runtime spawn-attestation, default-deny argument sanitizer. Defends against marketplace-poisoning + CVE-2025-69256.

    statusstableupdated2026-08-21installs787clones (14d)220groupsecurity

    npx -y mcp-server-attestation

    [details →](https://matthiasmeyer.tech/repos/mcp-server-attestation)[github ↗](https://github.com/studiomeyer-io/mcp-server-attestation)[npm ↗](https://www.npmjs.com/package/mcp-server-attestation)

- Long-term AI memory with knowledge graph, semantic search, entity tracking, session continuity. Drop-in for n8n.

    statusstableupdated2026-08-21stars2forks1installs870clones (14d)56groupworkflow

    npx -y n8n-nodes-studiomeyer-memory

    [details →](https://matthiasmeyer.tech/repos/n8n-nodes-studiomeyer-memory)[github ↗](https://github.com/studiomeyer-io/n8n-nodes-studiomeyer-memory)[npm ↗](https://www.npmjs.com/package/n8n-nodes-studiomeyer-memory)

- Multi-provider LLM, no memory required. For cross-session memory see n8n-templates.

    statusstableupdated2026-08-01clones (14d)15groupworkflow

    [details →](https://matthiasmeyer.tech/repos/n8n-workflows)[github ↗](https://github.com/studiomeyer-io/n8n-workflows)

- Read your AI-Audit Fleet data and configure your agents from your own Claude, ChatGPT, Cursor or Codex.

    statusstableupdated2026-08-21tools14installs225clones (14d)29groupsaas

    npx -y mcp-studiomeyer-agents

    [details →](https://matthiasmeyer.tech/repos/mcp-studiomeyer-agents)[github ↗](https://github.com/studiomeyer-io/mcp-studiomeyer-agents)[npm ↗](https://www.npmjs.com/package/mcp-studiomeyer-agents)

- Next lesson, quiz, review, certificates, tutor.

    statusstableupdated2026-08-15tools12stars1installs2kclones (14d)89groupsaas

    npx -y mcp-academy

    [details →](https://matthiasmeyer.tech/repos/mcp-academy)[github ↗](https://github.com/studiomeyer-io/mcp-academy)[npm ↗](https://www.npmjs.com/package/mcp-academy)

- Memory, CRM, GEO, Crew. 119 tools, 21 slash commands, 5 skills, 3 subagents. Magic Link auth. EU Frankfurt.

    statusstableupdated2026-08-19stars2forks1clones (14d)368groupsaas

    [details →](https://matthiasmeyer.tech/repos/studiomeyer-marketplace)[github ↗](https://github.com/studiomeyer-io/studiomeyer-marketplace)

- Knowledge Graph, semantic search, session tracking, multi-agent support. Hosted at memory.studiomeyer.io. Free tier.

    statusstableupdated2026-08-19tools56stars6forks1clones (14d)32groupsaas

    [details →](https://matthiasmeyer.tech/repos/studiomeyer-memory)[github ↗](https://github.com/studiomeyer-io/studiomeyer-memory)

- 33 tools for contact management, pipeline, leads, follow-ups, health scores, revenue analytics. Hosted at crm.studiomeyer.io. OAuth 2.1.

    statusstableupdated2026-08-19tools37stars3clones (14d)33groupsaas

    [details →](https://matthiasmeyer.tech/repos/studiomeyer-crm)[github ↗](https://github.com/studiomeyer-io/studiomeyer-crm)

- 25 MCP tools and 5 expert workflows. Check how 8 LLM platforms see your brand. Hosted at geo.studiomeyer.io.

    statusstableupdated2026-08-19tools30stars3clones (14d)37groupsaas

    [details →](https://matthiasmeyer.tech/repos/studiomeyer-geo)[github ↗](https://github.com/studiomeyer-io/studiomeyer-geo)

- 10 MCP tools, 8 personas, 3 workflows. Zero API cost. Free tier available.

    statusstableupdated2026-08-24tools16stars3forks1clones (14d)26groupsaas

    [details →](https://matthiasmeyer.tech/repos/studiomeyer-crew)[github ↗](https://github.com/studiomeyer-io/studiomeyer-crew)

- Foundation pillar 9. Closes the tool-injection-RCE class that sidecar scanners (mcp-armor) and stdio wrappers (mcp-stdio-shellguard) cannot catch. Synthesises per-tool policies from declared semantics and enforces them at execution time. MIT, TypeScript.

    statusalphaupdated2026-08-21installs424clones (14d)26groupsecurity

    npx -y mcp-rce-guard

    [details →](https://matthiasmeyer.tech/repos/mcp-rce-guard)[github ↗](https://github.com/studiomeyer-io/mcp-rce-guard)[npm ↗](https://www.npmjs.com/package/mcp-rce-guard)

- Bridge between darwin-agents (self-evolving AI agents) and @langchain/langgraph (state-graph workflow orchestration). Zero hard deps, both upstreams as peer-dependencies. Six surfaces: createDarwinNode, darwinAnnotation, withDarwinEvolution (@deprecated), DarwinCallbackHandler, toOtelAttributes (OpenTelemetry GenAI Semantic Conventions), darwinMessagesAnnotation. v0.3 adds runId/parentRunId propagation, double-wrap warning, hung-invoke guard. 132 tests, R1+R2 review loops, MIT.

    statusalphaupdated2026-08-21installs2.3kclones (14d)50groupagents

    npx -y darwin-langgraph

    [details →](https://matthiasmeyer.tech/repos/darwin-langgraph)[github ↗](https://github.com/studiomeyer-io/darwin-langgraph)[npm ↗](https://www.npmjs.com/package/darwin-langgraph)

- Five Temporal templates (T01-T05): memory-aware agent, operator approval, saga rollback, recurring synthesis, multi-agent coordination. All workflows write durable knowledge (learn), decisions (decide), and mistakes into Memory via Temporal activities. Bring-your-own backend via the MemoryClient adapter (HostedMemoryClient + InMemoryMemoryClient). 45 tests with time-skipping, MIT.

    statusalphaupdated2026-08-21stars1clones (14d)27groupworkflow

    [details →](https://matthiasmeyer.tech/repos/temporal-memory-workflows)[github ↗](https://github.com/studiomeyer-io/temporal-memory-workflows)

- Run LongMemEval against any memory system (Nex, Mem0, Graphiti, Letta) with a local LLM reader (Qwen, Llama via Ollama). 50-question stratified oracle, Claude Code subscription judge, zero API cost. Python, MIT.

    statusalphaupdated2026-08-03clones (14d)9groupmemory

    [details →](https://matthiasmeyer.tech/repos/nex-local-bench)[github ↗](https://github.com/studiomeyer-io/nex-local-bench)

- Nine LLM citizens build a small town. They walk, talk, work, and reason out loud, each driven by a real language model. Open-source mirror of the live meetmyagent.io world, built on darwin-agents and LangGraph. TypeScript, MIT.

    statusbetaupdated2026-07-10stars1clones (14d)6groupagents

    [details →](https://matthiasmeyer.tech/repos/polis-darwin)[github ↗](https://github.com/studiomeyer-io/polis-darwin)

- Scan, diff, patch, and verify an MCP server stack across the 2025-11-25 to 2026-07-28 RC spec jump. Eight detection rules, AST rewrite via ts-morph, CLI-first. Foundation pillar by StudioMeyer (MCP Factory). TypeScript, MIT.

    statusalphaupdated2026-08-21installs516clones (14d)57groupfactory

    npx -y mcp-stateless-migrator

    [details →](https://matthiasmeyer.tech/repos/mcp-stateless-migrator)[github ↗](https://github.com/studiomeyer-io/mcp-stateless-migrator)[npm ↗](https://www.npmjs.com/package/mcp-stateless-migrator)

- A Rust workspace: mcp-fuzz (a schema-aware fuzzer that finds crashes and hangs, SARIF output) and mcp-storm (a load tester with p50/p95/p99 and a CI gate), both on one shared async MCP client core (mcp-gauntlet-core). The pre-deploy counterpart to mcp-armor's runtime defense. 21 tests, three crates on crates.io, MIT.

    statusstableupdated2026-08-21installs40clones (14d)41groupsecurity

    cargo install mcp-fuzz mcp-storm

    [details →](https://matthiasmeyer.tech/repos/mcp-gauntlet)[github ↗](https://github.com/studiomeyer-io/mcp-gauntlet)[crates.io ↗](https://crates.io/crates/mcp-fuzz)

- Snapshots a server's tools/resources/prompts into a lockfile and fails CI on breaking changes, with direction-aware JSON-Schema classification (tightening an input schema vs loosening an output schema break different callers) plus a schema-hygiene linter. Single Rust binary, stdio + HTTP, SARIF + GitHub Action. 132 tests, on crates.io, MIT.

    statusstableupdated2026-08-21installs18clones (14d)35groupsecurity

    cargo install mcp-covenant

    [details →](https://matthiasmeyer.tech/repos/mcp-covenant)[github ↗](https://github.com/studiomeyer-io/mcp-covenant)[crates.io ↗](https://crates.io/crates/mcp-covenant)

- Scans your MCP server's source for the breaking-change signatures of the 2026-07-28 spec, then reports, file and line, what to change. It flags the retired -32002 error code (SEP-2164), stateful sessions (SEP-2575), deprecated roots/sampling/logging (SEP-2577) and OAuth without resource metadata (RFC 9728/8707). Every finding links its SEP/RFC. Single Rust binary, SARIF + GitHub Action. 93 tests, on crates.io, MIT.

    statusstableupdated2026-08-21installs39clones (14d)32groupsecurity

    cargo install mcp-herald

    [details →](https://matthiasmeyer.tech/repos/mcp-herald)[github ↗](https://github.com/studiomeyer-io/mcp-herald)[crates.io ↗](https://crates.io/crates/mcp-herald)

- A publish-readiness validator: checks server.json against the registry schema (required name/description/version, reverse-DNS name, packages/remotes, per-package registryType/identifier/transport, the snake\_case registry\_type mistake, mcpb fileSha256) and cross-checks version + mcpName consistency with the sibling package.json / Cargo.toml / pyproject.toml, so mcp-publisher accepts the upload first try. Single Rust binary, SARIF + GitHub Action. 166 tests, on crates.io, MIT.

    statusstableupdated2026-08-01installs42clones (14d)22groupsecurity

    cargo install mcp-passport

    [details →](https://matthiasmeyer.tech/repos/mcp-passport)[github ↗](https://github.com/studiomeyer-io/mcp-passport)[crates.io ↗](https://crates.io/crates/mcp-passport)

- Implements MCP spec SEP-414: propagates traceparent / tracestate / baggage from \_meta as OpenTelemetry spans, so host → server → tool → downstream renders as one trace tree. Drop-in for any MCP server, no vendor lock-in. 41 tests, MIT, TypeScript.

    statusstableupdated2026-08-15installs367clones (14d)51groupfactory

    npx -y mcp-otel

    [details →](https://matthiasmeyer.tech/repos/mcp-otel)[github ↗](https://github.com/studiomeyer-io/mcp-otel)[npm ↗](https://www.npmjs.com/package/mcp-otel)

- Enforces the allowed tool order, transitions, loop limits, and cost budgets at runtime. Fail-closed, so an agent cannot step outside its declared state machine. Zero-dependency core, LangGraph-aware. 74 tests, MIT, Python.

    statusstableupdated2026-08-01installs20clones (14d)12groupagents

    pip install statepilot

    [details →](https://matthiasmeyer.tech/repos/statepilot)[github ↗](https://github.com/studiomeyer-io/statepilot)[PyPI ↗](https://pypi.org/project/statepilot/)

- Implements MCP spec SEP-2549 (ttlMs + cacheScope): set the cache fields correctly server-side, and never share a private result across tenants or users client-side. Closes the cross-tenant cache-leak class with helpers and types. 66 tests, MIT, TypeScript.

    statusstableupdated2026-08-21installs386clones (14d)24groupfactory

    npx -y mcp-cache-kit

    [details →](https://matthiasmeyer.tech/repos/mcp-cache-kit)[github ↗](https://github.com/studiomeyer-io/mcp-cache-kit)[npm ↗](https://www.npmjs.com/package/mcp-cache-kit)

- Lints Claude Code SKILL.md, AGENTS.md, and subagent files: 25 rules, an A–F grade, prompt-injection and secret-leak detection, --fix, SARIF, and a GitHub Action. The CLI command is skilldoctor (the npm package is scoped). 91 tests, MIT, TypeScript.

    statusstableupdated2026-08-21stars1forks1installs468clones (14d)48groupsecurity

    npx -y @studiomeyer-io/skilldoctor

    [details →](https://matthiasmeyer.tech/repos/skilldoctor)[github ↗](https://github.com/studiomeyer-io/skilldoctor)[npm ↗](https://www.npmjs.com/package/@studiomeyer-io/skilldoctor)

- Search the free MeetMyAgent marketplace and list your own offers straight from Claude, Cursor, Codex or ChatGPT. Reads are anonymous, listing takes an optional key.

    statusbetaupdated2026-08-15tools7installs586clones (14d)75groupsaas

    npx -y meetmyagent-mcp

    [details →](https://matthiasmeyer.tech/repos/meetmyagent-mcp)[github ↗](https://github.com/studiomeyer-io/meetmyagent-mcp)[npm ↗](https://www.npmjs.com/package/meetmyagent-mcp)

- Calls the official Ahrefs remote MCP with a bearer token instead of an OAuth round trip, so scheduled jobs keep running unattended. Ships what the pricing page does not tell you: the real unit cost of each of the 41 tools, measured across 1,102 calls. Needs only bash, curl and python3.

    statusstableupdated2026-08-12clones (14d)7groupfactory

    [details →](https://matthiasmeyer.tech/repos/ahrefs-mcp-kit)[github ↗](https://github.com/studiomeyer-io/ahrefs-mcp-kit)

## Concepts

Repo-agnostic deep dives on the patterns behind the code.

- protocol

    ### What is MCP, actually?

    Model Context Protocol explained without the marketing. What it solves, what it doesn't, and when stdio beats HTTP.

    Read →

    https://matthiasmeyer.tech/concepts/what-is-mcp

- architecture

    ### Stdio vs HTTP for MCP

    Transport choice changes everything. Latency, security model, deployment story. A practical decision tree.

    Read →

    https://matthiasmeyer.tech/concepts/stdio-vs-http

- memory

    ### Memory architectures compared

    Local SQLite + FTS5, knowledge graph, vector embeddings, hybrid. Which fits which agent shape?

    Read →

    https://matthiasmeyer.tech/concepts/memory-architectures

- protocol

    ### Agent-to-Agent protocol v1.0 RC

    What an agent-card.json buys you, what it doesn't, and how it relates to MCP and WebMCP.

    Read →

    https://matthiasmeyer.tech/concepts/a2a-protocol

- browser

    ### WebMCP for browser agents

    W3C CG Draft, Chrome 146+. The proposal to give web pages a structured tool surface for in-browser agents.

    Read →

    https://matthiasmeyer.tech/concepts/webmcp

- agents

    ### Agent orchestration patterns

    Single agent, sequential pipeline, parallel fleet, judge-arbitrated. Trade-offs from running each in production.

    Read →

    https://matthiasmeyer.tech/concepts/agent-orchestration

## Books I wrote

Seven books on AI, Claude, AI visibility and memory-first systems. Plain language, no hype. Kindle eBooks on Amazon.

[All books →](https://matthiasmeyer.tech/books)

- ![The Website That Works: Build It With AI, Get Found by Everyone, Turn It Into Business](https://matthiasmeyer.tech/books/the-website-that-works-en.webp)

    ### The Website That Works

    Build it with AI, then make it earn

    $12.99

    https://matthiasmeyer.tech/books/the-website-that-works

- ![Claude Unlocked: Everything Claude Can Do, and How to Make It Work for You](https://matthiasmeyer.tech/books/claude-unlocked-en.webp)

    ### Claude Unlocked

    The complete handbook for non-coders

    $12.99

    https://matthiasmeyer.tech/books/claude-unlocked

- ![Build Your Own Jarvis: The memory-first AI system that remembers you, works while you sleep, and builds its own tools](https://matthiasmeyer.tech/books/jarvis-en.webp)

    ### Build Your Own Jarvis

    The memory-first system in practice

    $8.99

    https://matthiasmeyer.tech/books/build-your-own-jarvis

- ![Get Found by AI: The Discovery Stack Playbook](https://matthiasmeyer.tech/books/get-found-en.webp)

    ### Get Found by AI

    The Discovery Stack, layer by layer

    $12.99

    https://matthiasmeyer.tech/books/get-found-by-ai

- ![AI Without Bullshit: How to Use AI Properly](https://matthiasmeyer.tech/books/ai-without-bullshit-vol2-en.webp)

    ### AI Without Bullshit

    The practical half of the series

    $4.99

    https://matthiasmeyer.tech/books/ai-without-bullshit-vol-2

- ![AI Without Bullshit: How AI Really Works](https://matthiasmeyer.tech/books/ai-without-bullshit-vol1-en.webp)

    ### AI Without Bullshit

    Why AI guesses instead of knowing

    $4.99

    https://matthiasmeyer.tech/books/ai-without-bullshit-vol-1

- ![Codex Unlocked: The AI That Comes Free With ChatGPT, and How to Put It to Work Without Writing Code](https://matthiasmeyer.tech/books/codex-unlocked-en.webp)

    ### Codex Unlocked

    The AI you already pay for, no code

    $12.99

    https://matthiasmeyer.tech/books/codex-unlocked

## Sitemap

Every page of this site as Markdown: [sitemap](https://matthiasmeyer.tech/sitemap.md). Curated entry point: [llms.txt](https://matthiasmeyer.tech/llms.txt).