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.
-
MCP server for WHO Global Health Observatory (GHO) data access via the OData API. Provides search and retrieval of health indicators, country data, and regional statistics from the World Health Organization using modern OData protocol.
npm MIT -
A globally accessible Model Context Protocol (MCP) server providing comprehensive medical information from FDA, WHO, PubMed, and RxNorm APIs. Optimized for Indian medical context. Use with npx ithan_final anywhere.
npm ISC -
A globally accessible Model Context Protocol (MCP) server providing comprehensive medical information from FDA, WHO, PubMed, and RxNorm APIs. Optimized for Indian medical context. Use with npx mcp_ind_std anywhere.
npm ISC -
An MCP Server for Go developers who use Claude
MIT -
Use this MCP server to tell AI who are you.
-
🔍 A Model Context Protocol (MCP) server that provides semantic search capabilities for GitHub repository issues using FAISS and OpenAI embeddings. Perfect for developers who want to quickly find relevant issues, bug reports, and discussions across GitHub repositories using natural language queries.
MIT ★ 2 -
Shop a whole storefront by voice: an MCP server over Streamable HTTP, built for people who cannot use a screen
MIT -
Chatbot who uses MCP server from hf-articles-search repo with "fastapi-mcp" for RAG and embeddings search to answer question related to science articles from kaggle "News Category Dataset" from HuffingtonPost.
GPL-3.0 -
MCP server that routes US home emergencies to the right trade — who to call, in what order, first steps, and typical costs with dated sources.
MIT -
Agentic AI platform with MCP tool servers for vaccine coverage equity analysis using UNICEF (8.8M rows), WHO immunization, and OECD ODA financing data
-
A modular MCP based AI assisstant that fetches and reads those long official documentation in real time using MCP tools, web search, and async scraping. Designed for developers who want instant, context-aware answers straight from trusted sources.
-
Know what breaks before you change Salesforce. Ask your AI about your org: where a field is used, what runs on save, which Apex is dead, who can see what. Offline, read-only, cited. Open source (MIT).
npm MIT ★ 3 -
regulatory-change-intelligence-mcpgithub.com/apifyforge/regulatory-change-intelligence-mcpupdated this year
Regulatory change intelligence across 13 US federal data sources, delivered as an MCP server your AI agent can query directly. Built for compliance officers, GRC teams, and trade compliance operations who need forward-looking signals — not just a list of current rules.
MIT -
Export control screening MCP that checks transaction parties, classifies dual-use technologies, and detects diversion routes — all from a single MCP tool call. Built for export compliance officers, defense contractors, semiconductor companies, and customs brokers who need fast, evidence-backed screening decisions.
MIT -
A memory graph designed for the agent that uses it, not the human who feeds it. Engrama reconstructs context from associations on demand, replacing the "stuff everything into the prompt" reflex with targeted graph traversal. SQLite default, Neo4j optional.
pypi Apache-2.0 ★ 9 -
Using SDD? But Who checks that Specs out of the date? CatSpec Cares. Living specs linked to your code, with checks for TypeScript and C# and an MCP server for AI agents.
npm Apache-2.0 ★ 2 -
bullhorngithub.com/mean-weasel/bullhornupdated this year
Agent-first social media scheduler that works from your IDE via MCP. Not an auto-poster or AI slop machine — a workspace for thoughtful devs and product leaders who use Claude Code, Codex, and other agentic tools to craft, iterate on, and schedule real content alongside their code. iOS app included.
AGPL-3.0 ★ 4 -
humanpagesgithub.com/human-pages-ai/humanpagesupdated this year
MCP server (+ OpenClaw SKILL.md) that gives AI agents access to real-world people who listed themselves to be hired by agents. Search by skill/location/equipment, Post job offers & jobboard listings. Free tier / Pro subscription / x402 pay-per-use. Payments default to crypto (USDC) + other crypto + fiat supported.
npm MIT ★ 9 -
neruva-controlgithub.com/cloutsimlabs/neruvaupdated this year
Local loopback daemon for the Neruva substrate. Maintenance-only as of v0.10.0 -- the screen-control (Neruva Computer) and code-editing (Neruva Code) agents were retired in the 2026-05-18 substrate-first pivot and archived to _attic/. For new installs use neruva-mcp (Claude Code / Cursor / any MCP agent) or neruva-record (auto-record Claude Code sessions). The daemon still binds to 127.0.0.1:7331 with auth-token gating for users who want to host a local control plane for custom agents on the substrate.
pypi MIT -
mcpno update data
Read-only affiliate attribution and commission data for **iOS apps (StoreKit 2)** and **Shopify stores**. Attribloom attributes App Store subscriptions to the affiliate who drove them using the StoreKit 2 `appAccountToken` plus App Store Server Notifications v2, with no device fingerprinting. This server lets an agent read your campaigns, conversions, matured commissions, and payout eligibility. **Two of the seven tools need no API key**, so an agent can learn the integration before you have an account: | Tool | Needs a key | | --- | --- | | `get_started_guidance` | no | | `connect_store_guidance` | no | | `whoami` | yes | | `list_campaigns` | yes | | `campaign_readout` | yes | | `list_payouts` | yes | | `payout_eligibility` | yes | Money mutations (approving affiliates, creating campaigns, approving payouts) are deliberately not exposed. This server is read-only by design, and every figure it returns is read from the real ledger. Get an API key from the Attribloom dashboard under Settings, then API keys.
smithery -
Telegram AI CLI MCPgithub.com/stufently/telegram-ai-cli-mcpno update data
A CLI and MCP server, built from one Python codebase, for a personal Telegram account over MTProto (not the Bot API). Before the first start, sign in from a terminal with tg-ai account login; the server has no login flow of its own and will not work until that is done. Read tools cover chats, inbox, message search, who a username belongs to, group members, folders, drafts, scheduled messages, mentions, sessions and a waiting watch; an optional local archive answers searches offline. Anything that changes Telegram (sending, replying, joining, deleting, moderation) is a typed plan tool, available only under the plan profile: it records the intention, and a person applies it with tg-ai plan apply. No tool applies a plan, and reading never marks a chat read. Direct messages stay closed until allowlisted. Telegram may limit accounts it judges to be running abusive automation; use on your own account is at your own risk.
smithery -
Contextualno update data
## Contextual — Persistent Memory for AI Coding Agents AI coding agents forget everything the moment your session ends. **Contextual** fixes that by giving any MCP-capable AI client — for developers who use multiple AI coding tools at once — a real, persistent memory of your codebase: not just what the code says, but what changed and why. It's a **local-first MCP server**: your code, your index, and every query stay on your machine. The only network call is a lightweight, infrequent license check — no code, ever, leaves your device. Under the hood, Contextual builds a real understanding of your repository, not a text-similarity guess: - **Structural search** — tree-sitter AST parsing + call-graph resolution, so agents reason about how your code actually connects. - **Bitemporal history** — tracks not just when your code changed, but when the AI learned about it. Ask "did this bug fix happen before or after the agent's understanding of this function?" and get a real answer. - **Git-aware retrieval** — temporal, history-grounded context instead of a stale snapshot. - **Fast, self-contained** — index a 50k-line repository in about 5 minutes, then query it in ~94ms median, from a single ~0.8GB install. This extension connects Claude Desktop (or any MCP-capable client) to a Contextual installation already set up and activated on your machine — it does not provision Contextual from scratch.
smithery -
agentedgithub.com/frane/agentedno update data
A text editor for LLMs, not humans. Take ed, the line editor that nobody has voluntarily used since about 1975, and rebuild it for an environment where the typing user is a language model. Short verbs, line addresses, no modes, no TUI. What an editor optimises for changes when the user is the model: round trips per task, tokens per command, an editing buffer with a long memory, and an undo tree that remembers the branches the agent abandoned, because that's often where the interesting work was. ## Features - **Fewer round trips.** Read-before-Edit is unnecessary; on conflict the response carries the new content so you reconcile in one call instead of pre-reading every time. - **Branching undo.** Walked-back work stays addressable instead of being thrown away when you pick a different path. - **Three-way merge.** Concurrent agents get a structured conflict response instead of a silent overwrite. - **Atomic batches.** Multi-file refactors run all-or-nothing instead of leaving half-applied state on failure. - **Cross-file moves and regex replace as primitives.** Operations the built-in tools can't express cleanly become single calls. - **Drift detection.** External edits to an open file are folded into the tree instead of being clobbered by the next write. - **Inline diagnostics.** Type errors and lint findings surface on save, not at the next build many edits later. - **Cross-session memory.** Per-file notes persist between sessions and surface inline on the next open. - **Audit log.** Every operation recorded with actor and timestamp, so two agents in one workspace can't argue about who moved the head. ## Multi-workspace (v0.4.0) One MCP server registration handles every project you mention. Tool calls route to the workspace owning the absolute path you pass; each project gets its own SQLite, its own undo tree, its own LSP daemon — lazily spawned on first touch. Desktop hosts (Claude Desktop, Codex Desktop, Cursor) install the server once globally and use it across projects without per-project config. ## Install `ae` must be installed locally; this MCP bundle registers `ae serve` as a stdio server. ```sh brew tap frane/tap && brew install agented # or curl -sSL https://raw.githubusercontent.com/frane/agented/master/install.sh | sh ``` Pure Go, single static binary, Apache 2.0. Source: https://github.com/frane/agented
smithery -
Find which PyPI packages use a module, function or class, from the command line or as an MCP server.
pypi MIT