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.
-
Federated recall across an agent's brain, self, team, reading and code, in one budgeted query.
npm MIT -
recallgithub.com/Zavelinski/recallupdated this year
Zero-dependency MCP server for cross-session memory recall in Claude Code (lexical search/list/get).
MIT -
Ask Alexa+ whether your car, crib, food or medicine was recalled. MCP server (Streamable HTTP) for NHTSA, CPSC and FDA recall data. Amazon Developer Hackathon, Alexa+ track.
MIT -
One recall check across CPSC, FDA and NHTSA: match by name, model number, UPC or VIN.
MIT ★ 1 -
MCP server for Recall vector database with background indexing - search and index your code repositories and documentation
npm MIT -
Project memory that survives the session.
MIT -
EV-recall transport compliance — ADR Class 9 (UN3480/3481/3536/3556/3557/3558), DGSA workflow, thermal-runaway routing, OEM recall protocols. For UK car transporters under ADR 2025 + ZEV Mandate. By MEOK AI Labs.
pypi MIT -
MCP server for persistent synthetic memory -- attention-weighted recall across sessions using Ktor and Redis
AGPL-3.0 -
src-mcp-recall-mdgithub.com/kalikin-artem/src-mcp-recall-mdupdated this year
Local semantic search for markdown notes — MCP server
MIT -
Free, open-source flashcards with spaced repetition that your AI assistant fills through MCP. https://userecall.org
MIT -
recall-mcpgithub.com/autonsol/recall-mcpupdated this year
☁️ Persistent memory MCP server for AI coding agents
-
recallgithub.com/cognis-digital/recallupdated this year
Privacy-first local RAG over personal data — encrypted, audit-logged
NOASSERTION -
recall-kitgithub.com/zzusp/recall-kitupdated this year
An open-source toolkit that enables vibe coding to learn from past experiences rather than repeatedly trying and failing.
MIT ★ 3 -
local-recall-mcpgithub.com/Chikoku-NEKO/local-recall-mcpupdated this year
Fully local semantic memory for AI agents over MCP — Ollama embeddings, nothing leaves your machine
MIT -
Memory-Recallgithub.com/rebel0789/Memory-Recallupdated this year
Local-first repo memory and context for coding agents.
Apache-2.0 ★ 8 -
Store and search AI agent conversations to recover lost context and improve memory persistence in multi-agent workflows.
-
local-recall-mcpgithub.com/chikoku-neko/local-recall-mcpupdated this year
Fully local semantic memory for AI agents: search your notes and session logs from any MCP client, with embeddings served by Ollama
pypi MIT -
🎯 Federated recall across an agent's knowledge — cortex, agent-hq, scout and lens — in one token-budgeted query. CLI + web + MCP. Zero deps.
MIT -
Memory & RAG for Claude Code & Grok — mines transcripts into a local knowledge graph + MCP tools.
NOASSERTION -
Local memory for AI coding agents. Recall remembers your past sessions so your agent doesn't start from scratch every time.
MIT ★ 4 -
Save what you learn with Claude Code or Codex and review it with FSRS spaced repetition
-
Memory and state for AI agents: every correction kept with history, and agents that resume from their own records. Runs on your database.
pypi Apache-2.0 ★ 16 -
Local-first memory for DeepSeek Harness: per-turn BM25 recall you can audit — open-rate ledger, memory report, fail-closed write guard, 14-check doctor. Zero deps, no network, no model calls unless you opt in.
MIT -
ostk-recallgithub.com/os-tack/ostk-recallupdated this year
Local-first cross-corpus retrieval MCP server — model2vec embeddings + LanceDB (Tantivy BM25) + SQLite. One binary; hybrid (dense + BM25) search across markdown, code, and Claude Code sessions.
Apache-2.0 ★ 6 -
Hybrid semantic + keyword search over every chat you have (WhatsApp, Signal, iMessage, Instagram and more via Beeper), served to self-hosted agents over MCP. Postgres + pgvector.
MIT -
Your Claude Code memory, in every agent: read and write Claude Code auto memory (Markdown + [[wiki-links]]) from code or over MCP. Zero dependencies, no vectors.
npm MIT -
Your Claude Code memory, in every agent. Read and write Claude Code's auto memory over MCP (Codex, Cursor, ...) or from code. Markdown + wiki-links, zero dependencies.
npm MIT ★ 3 -
Shared memory for AI agents: Claude Code, Codex, Obsidian & GitHub in one searchable SQLite file, served over MCP. Handoff sessions between AIs. No vector DB.
MIT -
MCP server that gives Claude Code and GitHub Copilot a persistent, feature-scoped knowledge base — decisions, gotchas and constraints your agents read and write automatically across sessions.
MIT ★ 4 -
A local semantic-recall MCP server for citation-integrity academic writing — fastembed ONNX embeddings on LanceDB, cross-lingual, fully offline. Recall-only by contract: fragments carry file and page; the source PDF supplies every quote. Companion to alexandria. 服務引文完整性寫作的本地語意召回 MCP 伺服器:跨語言、完全離線;只召回不引用,片段附檔案與頁碼,每一句引文都回原始 PDF 取。
MIT ★ 1 -
Long-term memory for AI agents: facts with dates and sources, history kept, honest "I don't know". REST API, MCP server, TS/Python SDKs. Self-hostable. Website: https://recallmem.dev
NOASSERTION ★ 1 -
Local decision ledger for AI coding agents — keeps why a choice was made and which paths are dead ends, and re-injects it after context compaction. Plain Markdown, zero dependencies, works across Claude Code / Codex / Cursor / Copilot / Gemini.
MIT -
Recallgithub.com/adityapall1/Recallupdated this year
Recall is a personal knowledge base you can talk to. Save notes, snippets, and links, then search them by meaning rather than exact wording. Recall runs as an MCP server, so it works directly with your AI assistant, so you can ask Claude "what did I save about hash tables?" and get an answer from your own notes. There is also a CLI and web app.
MIT ★ 1 -
Persistent local memory for Claude Code. Total recall from your session files — no API calls, no summaries, no AI deciding what matters.
pypi MIT -
vin-mcpgithub.com/keptlive/vin-mcpupdated this year
Free VIN decoder MCP server — NHTSA, EPA, safety ratings, recalls, fuel economy, vehicle photos
npm MIT -
FDA drug label answers with section citations, RxNorm name resolution, recalls and shortages.
MIT ★ 1 -
MCP server giving AI agents real vehicle data — specs, federal recalls, and OBD-II DTC reference. npx -y carvector-mcp
MIT ★ 1 -
Local-first memory for AI agents. Keep decisions and evidence across sessions. Recall with sources through MCP.
AGPL-3.0 ★ 9 -
agent-memorystore-mcpgithub.com/mdfifty50-boop/agent-memory-mcpupdated this year
MCP server providing persistent cross-session memory for AI agents — store, recall, search, and summarize memories across agent boundaries
npm MIT -
looktwice-mcpgithub.com/eason4kim-rocket/looktwice-mcpupdated this year
MCP server for the LookTwice API: email, EU VAT, IBAN, and domain validation plus evidence-backed CPSC recall screening from any MCP client.
MIT -
MCP server for U.S. vehicle records: NHTSA recalls, service bulletins, trouble codes, VIN decode, EPA fuel economy and crash ratings. Free, no API key.
MIT ★ 1 -
mcp-server-openfdagithub.com/janiumang/mcp-server-openfdaupdated this year
MCP server exposing openFDA pharmacovigilance data (FAERS adverse events, drug labels, drug recalls, ROR signal detection) as structured tools for Claude and other MCP-compatible clients.
pypi MIT -
Describe a car problem and see the official NHTSA recalls and owner complaints that match it. A measured AI model, a website that runs in the browser, and an MCP server for AI assistants.
MIT -
MCP server and CLI for Hunt Auto Group Texas: used-car data for Central Texas buyers (NHTSA recalls and crash stars, EPA MPG, size by model year) and buying guides. Read-only, no key.
npm MIT -
MCP server for the ScalpStream scouts: fuel prices (ES/FR/IT/US), air quality, US border wait times and US product recalls, paid per query over x402 (USDC, XRP, RLUSD, Solana).
MIT -
The agent memory that takes it back: correct a fact once and the retired value stops coming back, by key, with no LLM in the loop. Long-term memory for AI agents in a zero-dependency single file + MCP server, with value-ranked recall, per-type decay, consolidation, revert, and tamper-evident erasure.
pypi MIT -
Persistent-memory (SQLite) MCP server, derived from `my-local-storage-mcp`. Features the same tools (`remember_fact`, `recall_facts`, `recall_by_topic`), the same consolidation logic, and the same plugin system.
GPL-3.0 -
Agent memory with a recall button - Every memory knows its sources. Recall a bad source, and everything learned from it goes too
Apache-2.0 ★ 6 -
lossless-claudegithub.com/offendingcommit/lossless-claudeupdated this year
Cross-runtime memory bridge between Claude Code and OpenClaw via the lossless-claw LCM SQLite database. MCP recall tools, PreCompact capture hook, SessionStart bootstrap, lcm-recall skill.
Apache-2.0 ★ 1 -
An MCP server that turns Alexa+ into a recall guardian for everything in the home: official CPSC, NHTSA and FDA recalls, matched carefully, with proactive alerts. Serverless on AWS.
MIT -
Persistent per-project memory for Claude Code, Kiro, Cursor & Codex - plain markdown committed with your code, captured prompt-free, auto-injected at session start, recalled by meaning (local semantic search, zero API). Cross-project persona, cited recall, searchable session history.
MIT ★ 7 -
fridaigithub.com/chloeeekim/fridaiupdated this year
Local MCP server for recalling past code, commits, and AI conversations — search-only, no local LLM required
pypi MIT License -
Vestigegithub.com/samvallad33/vestigeno update data
Local-first Rust MCP. Causal Backfill / event-anchored memory. Tools: recall, smart_ingest, backfill. Local stdio. Package 2.8.0.
smithery -
Run local MCP for hexdocs digest, hex-search, gh-search, remember and recall learnings
MIT -
An MCP server that uses a knowledge graph to store and recall structured memory for AI models
npm MIT -
MCP server: Access FDA data on drugs, devices, food recalls, and adverse events via openFDA.
Apache-2.0 -
Your portable AI memory layer. Classify, store, and recall what matters across models, tools, and devices.
pypi MIT -
Conversational MCP server for pharmacovigilance research using public openFDA safety, label, and recall data.
MIT -
MCP server: 10 public-money tools - grants, contracts, SAM.gov, SBIR/STTR, SEC financials, recalls, EU tenders.
pypi MIT -
memotrustgithub.com/idanref/memotrustupdated this year
Verified memory for AI agents — agents propose, evidence verifies, recall returns only earned trust.
npm MIT