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.
-
context-fabricgithub.com/vikas9793/context-fabricupdated this year
Context synchronization layer for AI coding agents — ensure project continuity and eliminate memory drift automatically.
npm MIT -
Sip your tokens, don't gulp them. Keep Claude Code's context clean: drift detection, re-read dedup, integrity scoring, AST-aware reads, and 16 MCP tools for Claude Desktop.
npm MIT -
Append-only agent journal, gated mode passports and a document index in one MCP server. Keeps 1,558 specs and reports (4.5M tokens) out of context: 123 tokens of metadata per document, drift caught by SHA256, 95.75% less to read.
MIT -
The plan-of-record for AI coding agents — spec, plan, and drift detection that survive context resets. File-based, git-versioned, MCP-native.
MIT -
Codex-native codebase intelligence: deterministic repo context, change-plan drift review, and verification gating for AI coding agents. Local-first, zero API keys.
MIT ★ 2 -
Keep Claude Code context clean. Open-source toolkit: drift detection, re-read dedup, integrity scoring, AST-aware reads, 15 MCP tools. 62.6% measured savings, reproducible.
MIT ★ 46 -
@isaacriehm/cairn-coregithub.com/isaacriehm/cairnupdated this year
Cairn core — state + context layer. Curated `.cairn/ground/` (decisions, §INV invariants, canonical-map, brand, quality-grades), MCP server, init wizard, hook runners, sensors, GC drift sweep.
npm MIT -
Task-Anchor-MCPgithub.com/Kodaxadev/Task-Anchor-MCPupdated this year
ADHD executive function enforcement for Claude Desktop. An MCP server with task locking, drift detection, and stateful boundaries to stop context switching.
MIT ★ 3 -
Comment directives in, compact AI context out — a drift-aware code graph for JS/TS that gives Claude, Codex & other assistants a small query pack instead of the whole tree. CLI + MCP server.
MIT -
MCP Task Relay is a production-ready Model Context Protocol (MCP) server that exposes a sophisticated scheduler/executor workflow for autonomous agents. Built with enterprise-grade reliability, it features an intelligent Ask/Answer protocol with cryptographic context verification, preventing context drift while reducing token usage by 95%+.
MIT ★ 1 -
Scythe (ctx) is a live, auto-updating codebase context engine. It maintains a local SQLite relational graph of your repository, synced dynamically on edit by AI models, guaranteeing structured, zero-drift context under 10k tokens — even for million-line codebases.
Apache-2.0 -
Retrieval Context Provenance Auditor — MIT reference implementation of the public SHPBL behaviour specification. Influence attribution, lineage, advisory source trust and retrieval drift for agent retrieval supply chains. Zero runtime dependencies.
MIT -
@psno/subconductorgithub.com/paulbenchea/mcp-subconductorupdated this year
Subconductor is an MCP server that acts as a Persistent State Machine for AI agents. It prevents 'context drift' by externalizing the task list into a Markdown table manifest, supporting batch operations, dynamic custom columns, task IDs, and non-linear e
npm Apache-2.0 -
mcp-subconductorgithub.com/PaulBenchea/mcp-subconductorupdated this year
Subconductor is an MCP server that acts as a Persistent State Machine for AI agents. It prevents "context drift" during long refactors by externalizing the task list into a physical manifest. It enables non-linear execution, allowing agents to handle dependencies dynamically while maintaining a transparent, resumable audit trail.
Apache-2.0 ★ 2 -
everspring-mcpgithub.com/alpeerkaraca/everspring-mcpupdated this year
everspring-mcp is a production-oriented Model Context Protocol (MCP) server built to provide AI agents with accurate, version-specific Spring ecosystem documentation. Its primary objective is to reduce hallucination and version drift by grounding responses in a curated, indexed documentation base rather than relying on model memory.
★ 1 -
autologygithub.com/Curt-Park/autologyupdated this year
A Claude Code plugin that turns AI-assisted work into a shared living ontology. Captures decisions, conventions, and context autonomously into typed, interlinked knowledge nodes (git-committed markdown). Navigate the ontology as a graph, trace conceptual paths between ideas, and catch doc-code drift before every commit.
MIT ★ 25 -
limpsgithub.com/paulbreuler/limpsupdated this year
limps your Local Intelligent MCP Planning Server across AI assistants. No subscriptions, no cloud—run it locally. Version control your planning docs in git. No more context drift—one shared source of truth across Claude, Cursor, Copilot, and any MCP tool.
npm MIT ★ 10 -
Vetono update data
93 agentic MCP tools + 49 specialist agents for every major AI CLI — self-learning, no API keys. Veto gives Claude Code, Codex CLI, Gemini CLI, Cursor, Windsurf, Zed, and JetBrains a council of specialist agents, persistent cross-platform memory, a self-learning router, CI/CD gates, and dependency-hallucination + decision-drift guards — all powered by your existing AI subscription. No separate API keys, no extra billing. **Highlights** - **Council debate** — multi-agent GREEN/YELLOW/RED verdicts on risky changes (LLM-backed via MCP Sampling, with deterministic fallback) - **Cross-platform memory & session handoff** — save on Claude, resume on Gemini or Codex; nothing needs re-explaining - **Self-learning router** — improves task routing from recorded outcomes - **Guards & gates** — CI gate, diff review, secrets scan, dependency-hallucination verification, decision-drift enforcement - **Compact mode** — advertise 9 tools instead of 93 and save ~16K context tokens; every tool stays callable **Links**: [GitHub](https://github.com/jigyasudham/veto) · [npm](https://www.npmjs.com/package/@jigyasudham/veto)
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 -
Codebase intelligence for AI. Detects patterns & conventions + remembers decisions across sessions. MCP server for any IDE. Offline CLI.
MIT ★ 795 -
First-hand observations of public MCP servers: what tools each declared, byte-exactly, and when that declaration changed. Declarations, not behaviour.
-
Detect configuration drift across environments before it causes incidents
MIT ★ 4 -
Real-time AI conversation drift monitor — MCP server for Claude Code, Gemini CLI, Codex CLI, and Cursor
npm ISC -
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 -
driftguard-mcpgithub.com/jschoemaker/driftguard-mcpupdated this year
MCP server for DriftGuard — exposes AI conversation drift scores and session health to Claude Desktop and other MCP clients
★ 7 -
Local JSON schema diff CLI + MCP client for API/MCP drift — offline compare_json, hosted monitoring connector for Pro/Team.
MIT ★ 2 -
A stdio MCP server for repo-local tldraw diagrams, portable SVG previews, and code graph drift detection.
npm MIT -
embspec-mcpgithub.com/MukundaKatta/embspec-mcpupdated this year
MCP server: embedding pipeline ops + drift detection for production RAG. Assert query encoder matches index manifest; compute retriever stability between two index versions. Wraps embspec.
MIT -
Local CLI and MCP server that packs a repository into budgeted Markdown parts, writes a manifest of every included and skipped file with the reason, masks secrets in place, and exits non-zero when the snapshot drifts. For Claude, ChatGPT, Cursor and CI.
npm MIT ★ 2 -
@mukundakatta/embspec-mcpgithub.com/mukundakatta/embspec-mcpupdated this year
MCP server: embedding pipeline ops + drift detection for production RAG. Assert query encoder matches index manifest; compute retriever stability between two index versions on a frozen probe set.
npm Apache-2.0 -
MCP server for AI Stupid Level: LLM leaderboard, model history, drift status, incidents and provider status from the ASL Data API, plus route previews and prompts through the ASL Smart Router.
npm MIT -
@lulzasaur9192/agent-infra-mcpgithub.com/lulzasaur9192/agent-infra-mcpupdated this year
MCP server with 18 tools for AI agent infrastructure — persistent memory, API drift detection, and HMAC-signed trust receipts
npm MIT -
Persistent session memory for AI coding agents — local-first, with on-device inference, associative recall, and drift detection. Works with Claude Code, Cursor, and Codex.
npm Apache-2.0 ★ 156 -
Free MCP server for engineers running AI in production: price a model, size a GPU, audit your MCP config, explain network config drift. No account, no telemetry.
MIT -
Free read-only MCP server for network engineers: config drift, CIS/PCI checks, 802.1X diagnosis, certificates inside configs, topology, OPNsense rule changes, change pre-flight. No account, no telemetry.
MIT -
Pre-execution governance for AI agents. Intercepts MCP tool calls before execution with deterministic blocking, human-in-the-loop holds, and behavioral drift detection.
npm MIT -
querybridge-mcpgithub.com/mahmoudhassanmustafa/querybridge-mcpupdated this year
MCP server connecting Claude Code with MySQL — supports SSH tunnels and multiple databases
npm MIT -
architecture-intelligence-platformgithub.com/michaelegner/architecture-intelligence-platformactive
Trusted architecture context for AI agents: an evidence-backed architecture graph from OpenAPI, AsyncAPI and OpenTelemetry, served over MCP.
Apache-2.0 ★ 10 -
Behavioral safety, vulnerability probing, and product-risk auditing platform & MCP server for Generative AI & Large Language Models.
Apache-2.0 ★ 2 -
Token-budgeted, drift-aware MCP memory engine for AI coding agents. Backed by SQLite WAL + FTS5 BM25, Git-anchored drift webhooks, and 1-click onboarding.
AGPL-3.0 -
Behavioral safety, vulnerability probing, and product-risk auditing platform for Generative AI & Large Language Models.
pypi Apache-2.0 -
MCP server for MCP Server Change and Health Monitor. Checks MCP servers for uptime and tool changes, with breaking changes marked. Runs on Apify.
npm MIT -
Bind documentation claims to code fingerprints. Catch stale CLAUDE.md, AGENTS.md and docs at write time inside Claude Code and Codex, with a tamper-evident history.
npm MIT -
Bind documentation claims to tiered code fingerprints. Catch stale CLAUDE.md, AGENTS.md and docs at write time inside Claude Code and Codex, with a tamper-evident history.
npm MIT ★ 3 -
mysql-mcp — MCP server connecting Claude Code to MySQL. Supports SSH tunnels, SSL/TLS, and multiple databases. 20 tools for schema introspection, query execution, ERD generation, stored procedures, triggers, and events. Includes CLI for connection management.
MIT ★ 1 -
MCP server for CloudFormation drift reporting and plan-then-execute promotions
npm MIT -
driftos-mcp-servergithub.com/DriftOS/driftos-mcp-serverupdated this year
MCP server for conversational memory and semantic drift detection in AI agents.
★ 2 -
Local-first MCP server: hash-chained document store with signed retrieval receipts and an agent orient (staleness/drift) protocol.
npm Apache-2.0 -
Persistent ground truth for Claude Code. Stop AI agents from drifting on your codebase.
MIT ★ 6 -
Read-only-first MCP server for Sonatype Nexus Repository 3: inventory, audit, architecture docs and drift checks
MIT -
fastlane for MCP servers: preflight against every store's rejection causes, publish where you can, prepare the rest, catch listing drift. CLI + MCP server.
MIT ★ 3 -
scope-guard-mcpgithub.com/mdfifty50-boop/scope-guard-mcpupdated this year
MCP server that enforces multi-agent scope boundaries — prevents scope drift, work duplication, and infinite delegation loops in agentic systems
-
studio-mcpgithub.com/rishbjain1/studio-mcpupdated this year
Block-method film pipeline as MCP tools: plan → lock → render (Higgsfield Soul) → style-drift QC → cut. Provider-agnostic LLM layer.
MIT ★ 2 -
Semantic code graph for AI agents — deterministic FQN resolution, impact analysis and architectural drift gates, exposed over MCP.
pypi MIT -
Insitu keeps your AI instructions and skills in one vault, and every project subscribes to exactly the set it needs, so guidance stops drifting between projects.
MIT -
Contacts for AI agents: people, promises, yearly dates and a radar for who is drifting. SQLite, zero deps, MCP server.
npm MIT ★ 1 -
acd-persona-generator-mcpgithub.com/agent-character-design/acd-persona-generator-mcpupdated this year
MCP server for ACD-compliant AI agent persona specs. Level 2 loop design, drift defense, behavioral memory. Not just system prompts.
MIT -
couchloop-eq-mcpgithub.com/wisenbergg/couchloop-mcpupdated this year
Behavioral governance layer for LLMs - monitors for hallucination, inconsistency, tone drift, and unsafe reasoning while managing stateful AI sessions
npm MIT -
Pre-execution governance for AI agents. Sub-millisecond tool call validation, drift detection, circuit breakers, human-in-the-loop holds. 829 tests. 56 MCP tools.
npm MIT ★ 1 -
ServiceNow MCP server with safe AI writes (plan, token, apply, journal, revert), find usages, flow tracing and drift checks over the full REST surface.
GPL-3.0 ★ 12