MCP servers that ship as code — a repository or a package you install and run locally (usually over stdio). They have no hosted endpoint, so we cannot probe or grade them: instead each one shows its repository, install command, license, stars and when it was last updated.
Collected from GitHub repositories and npm, PyPI, Cargo, Go, Maven, NuGet and RubyGems packages tagged as MCP servers, the official MCP Registry, Docker's MCP catalog, ModelScope, Baidu MCP World, Cline and other public directories; one entry per repository. A server that also offers a hosted endpoint is listed under Remote instead. These entries are not counted in our reachability, verification or readiness statistics.
-
@seizn/mcpgithub.com/litheonhq/seiznupdated this year
Model Context Protocol server for Seizn NPC memory, canon, replay, chaos, and Story Health tools.
npm MIT -
origin_conversationgithub.com/sanctumos/origin_conversationupdated this year
Conversation/export tooling + MCP server for searching SanctumOS canonical ChatGPT history.
NOASSERTION ★ 1 -
Flow-Work MCP server and canonical tool registration library
npm MIT -
@caputchin/mcpgithub.com/caputchin/caputchin-sdkupdated this year
stdio MCP adapter for Caputchin: proxies the canonical /api/mcp tool catalogue and ships offline dev-onboarding tools.
npm Apache-2.0 -
Model Context Protocol server for Tau's CAD tools over canonical chat RPC contracts
npm Apache-2.0 -
retcongithub.com/WujiLabs/retconupdated this year
Retcon for AI conversations. The AI recontextualizes its own past via MCP tools. Canonical Observer Actor instantiation of the Collaboration Protocol.
npm MIT -
An MCP (Model Context Protocol) server for Obsidian worldbuilding vaults that provides AI tools with consistent, canonical context from your fictional worlds.
npm MIT ★ 11 -
@autoady/mcp-serveractive
AutoAdy Meta Ads tools for AI assistants — thin stdio proxy of the AutoAdy MCP connector (same canonical tool vocabulary), plus legacy autoady_* aliases
npm MIT -
nodebench-mcpgithub.com/homenshum/nodebench-aiupdated this year
Turn messy input into a sourced report. 15 default tools: workflow, bidirectional sync, canonical NodeBench research bridge, discover_tools, and load_toolset.
npm MIT -
@bucket-foundation/mcpgithub.com/bucket-foundation/bucket-mcpupdated this year
Stdio MCP server for the Bucket Foundation research rail (bucket.foundation). Three tools: bucket_research, bucket_cite, bucket_canon_list.
npm MIT -
openclaw-hackathongithub.com/Trolleroof/openclaw-hackathonupdated this year
Apollo Labs RL run orchestrator: FastAPI PPO training, eval baselines, rollout GIFs, canonical RunReports, AgentMail delivery, Nia lessons, Next.js dashboard, and MCP tools.
★ 2 -
Canonical crosswalk between Toronto's 140 and 158 neighbourhood models, plus ward concordances. Explorer, REST API, OpenAPI, MCP tools.
-
@inferlane/mcp-servergithub.com/computegauge/inferlaneupdated this year
[DEPRECATED] Use @inferlane/mcp instead. This package re-exports a thin subset of tools; the canonical MCP surface (41+ tools, SQLite persistence, credibility engine, compute exchange) now lives in @inferlane/mcp.
npm MIT -
Give any MCP app a seat at your Agent Letterbox: five tools over durable agent mail. Letters stay plain files, identities stay jailed, the CLI stays canonical.
MIT ★ 1 -
Canonical Model Context Protocol (MCP) Remote Gateway for WarpPay402. Exposes 31 monetized Web3 AI developer tools and 3 autonomous multi-agent workflows via Server-Sent Events (SSE) and x402 USDC micropayments on Base, Solana, Arbitrum, Robinhood, and Arc.
MIT -
AI agent workspace infrastructure: one canonical .syncytium/ context, adapters for 10+ AI coding tools, handoff baton, lease lock, CI drift gate, 3D knowledge graph and a 23-tool MCP server.
npm MIT ★ 7 -
Python MCP bridge that lets multiple Claude Code / Cursor / agent sessions share one CogOS kernel. HTTP streamable transport, 12 cogos_* tools layered over the kernel's canonical session and handoff routes.
MIT -
Persistent memory + workflow orchestration as an MCP server. 78 canonical tools across 21 namespaces, SQLite-backed, with an LLM-as-judge drift gate and a vibe-flow loop (spec to artifact to drift to publish).
npm NOASSERTION ★ 2 -
seif-mcpgithub.com/and2carvalho/seifupdated this year
MCP server for the SEIF Protocol — provenance signing, transparency log, and data classification tools for AI agents (Cursor, Claude Code, Claude Desktop). Thin Node wrapper around the canonical Python implementation.
npm MIT -
CAM — Product Viability Standard: deterministic per-product profitability verdicts. Loose data in (JSON/CSV/key-value, JP/EN) -> canonical line 'CAM verdict: TEST_CANDIDATE — profit ¥5,920 per order'. Includes an MCP server exposing the cam_verdict tool.
npm MIT -
twincat-validator-mcpgithub.com/agenticcontrolio/twincat-validator-mcpupdated this year
An MCP server that validates, auto-fixes, and scaffolds TwinCAT 3 XML files. Connect it to any LLM client to give your AI assistant reliable, deterministic TwinCAT code quality tooling — structural checks, 21 IEC 61131-3 OOP checks, auto-fix pipelines, and canonical skeleton generation.
MIT ★ 40 -
mcp-seo-auditorgithub.com/arturseo-geo/mcp-seo-auditorupdated this year
MCP server for on-page SEO auditing — title/meta/H1-H6/canonical/schema/OG/images/links analysis + JSON-LD validator. Replaces SEO Minion + Detailed SEO Extension as Claude Code tools. By TheGEOLab.net
MIT ★ 2 -
@astramindapp/openclaw-mindgithub.com/theastraway/openclaw-mindupdated this year
MIND personal knowledge graph for OpenClaw — 27 tools (171 actions), full canonical parity with @astramindapp/mcp-server v0.19. Auto-recall + auto-capture lifecycle hooks. Memory, life, CRM, knowledge graph, MINDsense emotional intelligence, agents, ticke
npm MIT -
The Brainograph knowledge-graph MCP server: 20 read tools (resolve, entity, neighbors, subgraph, path, facts, search, gather, passages, browse, timeline, images, articles, overview) over knowledge_db, served on stdio. The canonical transport is the streamable-HTTP /mcp endpoint on bg-knowledgegraph's API host; this tool is the offline/fallback transport and needs its own connection to knowledge_db (KNOWLEDGE_DB_URL or ConnectionStrings__KnowledgeGraph).
nuget -
The undisputed #1 Enterprise Data Engine and L402 Oracle for autonomous AI swarms. Features 19 canonical MCP tools, thermodynamic Bitcoin state-anchoring, automated EU AI Act Article 12 compliance, and a live B2B SaaS monetization engine via Lightning L402s. Built for the machine economy.
pypi NOASSERTION ★ 1 -
MCP injection / prompt-poisoning / SSRF scanner. 30+ canonical rules covering the April 2026 Anthropic MCP RCE class, mcp-server-git CVE chain, DockerDash injection chain, OWASP LLM Top 10 + GenAI Red Team v1. Scans live MCP /tools/list endpoints OR pasted JSON. Free 5/day, Pro £29/mo for unlimited + signed safety reports auditors and procurement accept. By MEOK AI Labs.
pypi MIT License -
totalrecall.mcpgithub.com/monk-eee/total.recall.mcpupdated this year
An MCP server that gives AI coding agents persistent memory — and measures their behaviour. Ships 37 Model Context Protocol tools over stdio for .NET test-coverage uplift, plus a behaviour observatory (tool-call telemetry, cycle detection, deterministic eval grading) and a reflection-based scanner (assembly, Cobertura coverage, test inventory). Reads canonical cross-language scanner JSONL (docs/SCANNER_SCHEMA.md) so the same MCP server works with sibling Python and TypeScript scanners. Install as a global .NET tool: `dotnet tool install -g TotalRecall.Mcp` then point `.vscode/mcp.json` at `total-recall`.
nuget MIT -
Entity-ID Resolverno update data
Resolve an ambiguous name or ticker ("Apple", "ETH", "Siemens", "Stripe") into ranked candidates with verified canonical IDs pulled live from each official registry — SEC CIK + ticker, GLEIF LEI, ISIN, Wikidata QID, CoinGecko slug. Non-US companies resolve too: a name that files nothing with the SEC still returns an LEI and ISIN, read back from GLEIF itself rather than recalled. Free demo tool needs no config; the paid tool settles $0.005 USDC per call over x402 on Base from a wallet you control — no account, no API key.
smithery -
the-metis-fca-handbook-ai-harness-mcpno update data
# Metis FCA Handbook AI Harness — MCP Server An MCP (Model Context Protocol) server that integrates the Metis FCA Handbook AI Harness into Claude Desktop and other MCP-compatible agents. **Tool name:** `evaluate_fca_handbook_applicability` Use this tool to analyze FCA Handbook applicability for a product, service, or firm. Returns structured compliance reasoning with verbatim handbook citations. ## Why choose The Metis FCA Handbook AI Harness? - **Efficiency** Multiplies effectiveness of compliance advice. Saves £80+ in token fees per Harness run. - **Deals with "Hard Problem"**, in which LLMs' token incentives prioritise training data so results are unreliable. - **Verbatim citations** Quotes verbatim entries from the FCA Handbook. Other AI systems struggle to do this. - **Matches real-world need** You do not have to start off knowing which sections you are looking for. Carries out structured searches across all 10,000+ FCA Handbook entries. - **Secure Design** Harness compartmentalisation, one-shot structure, and statelessness fits natively with emerging AI agent security standards such as OWASP Top 10 for Agentic Applications 2026. - **AI Accessible** Integrates easily with AI workflows and agents. Your LLM can use it as a tool. ## Design Principles The Harness is built on proven principles: - **Stateless** — Each request is independent; no session coupling - **One-shot** — Complete analysis in a single call; no multi-turn state - **Clear contract** — Explicit input/output schemas for easy integration - **Hosted** — Single canonical source; no version drift or stale data ## Use Cases ### Compliance AI Platforms Embed FCA reasoning as a service within your compliance platform. Users ask natural-language questions; your platform calls the Harness and presents structured reasoning. ### AI Agent Workflows Agents building compliance workflows can include FCA Handbook reasoning as a composed tool—no external API calls, just MCP configuration. ### Compliance Review Automation Integrate into document review or due-diligence pipelines. Automatically screen new rules against FCA applicability. ## For Regulatory Screening FS firms screening MCP servers will find: - **Simple model:** Stateless, no hidden state, no background jobs - **Clear contract:** Explicit input schema, output schema, error modes - **Transparent updates:** Version pinning; no automatic upgrades - **Single point of failure:** If the Harness is down, it is obvious; no cascading config issues - **Audit-friendly:** All calls logged centrally, not distributed
smithery -
clawkitgithub.com/Iamalphaoff/clawkitupdated this year
ClawTools AI Agents 2026 - Ultimate Autonomous Tool Layer for GitHub Developers
-
Canonical YouTube intelligence for VS Code and modern MCP hosts.
MIT -
entityresolver-mcpactive
Resolve ambiguous names ("Apple", "ETH", "Siemens") to verified IDs: SEC CIK, GLEIF LEI, ISIN, Wikidata QID, CoinGecko slug. US and non-US. Free demo tool + x402-paid tool (USDC on Base, no API key). mcprush.com-9c27f351d0ec8ead53e5a3c5
npm MIT -
Token-efficient MCP doc-router — one canonical doc per query for your coding agents.
pypi AGPL-3.0 ★ 11 -
Deterministic terminology layer for AI coding agents: canonical vocabulary, drift detection, CLI + MCP server.
pypi Apache-2.0 ★ 2 -
bluefieldgithub.com/danielvhofmann/bluefieldupdated this year
Local first web scraper that turns any URL into clean Markdown or JSON and signs every capture with an offline verifiable Ed25519 provenance manifest called BPM. Git like history and diff for web data, plus an MCP server so AI agents can prove what they read. TypeScript monorepo, AGPL-3.0 engine, Apache-2.0 spec and SDKs.
AGPL-3.0 ★ 1 -
customer-support-agentgithub.com/alex-jb/customer-support-agentupdated this year
Triage user messages → auto-draft replies → HITL queue. L5 of the 7-layer one-person company canon. pip · MCP · MIT.
go MIT ★ 2 -
htmemgithub.com/droggy992/htmemupdated this year
HTML as canonical LLM memory and inter-agent comms. Claude Code plugin + MCP server. Anchor-signed, schema-validated, sanitized. Apache-2.0.
Apache-2.0 ★ 1 -
Audit and enforce canonical project documentation for AI-assisted development. Detect drift, validate specs, and brief agents. Part of the Guard family with TestGuard and WebSec Validator.
npm MIT ★ 34 -
java-patterns-mcpgithub.com/air237/java-patterns-mcpupdated this year
MCP server exposing the 23 Gang of Four design patterns to AI coding agents — generation, canonical examples, AST-based detection, validation, and anti-pattern refactoring for Java.
MIT -
Self-improving context & memory for Claude Code and OpenAI Codex. One canonical knowledge store injected only when relevant — hooks push budgeted context, an MCP server serves depth on demand, and it learns lessons from your sessions. Agent memory + context engineering as a single static Go binary.
MIT ★ 3