AI and memory servers store what an agent learns, retrieve from vector indexes, or call other models. Note where embeddings are computed and where memories are stored before you connect one. 3557 published MCP servers match this ranking. The highest trust scores right now are memory-mcp at 67, context-doctor at 67, Codex Delegate at 67. The order is the published trust score: registry record, license, maintenance, popularity, documentation, and security signals. Featured slots, when an editor sets them, are labeled and do not change the score. Best AI and memory MCP servers is not a paid placement.
Best of
Full ranking
Every server that matches this ranking, ordered by trust score.
MCP server for Anthropic's Claude Fable, Opus 5, and multi-model reasoning councils.
Registry
–License–Quality–MaintenanceLicense: Not graded. No license is recorded for this server.Quality: Not graded. No README or tool list has been captured yet.Maintenance: Not graded. No commit or release date has been recorded.
Undetectable browser automation for LLM agents, spoken over MCP.
Registry
–License–Quality–MaintenanceLicense: Not graded. No license is recorded for this server.Quality: Not graded. No README or tool list has been captured yet.Maintenance: Not graded. No commit or release date has been recorded.
Persistent memory for AI agents — audio intelligence + Music Memory ingestion and recall
Registry
–License–Quality–MaintenanceLicense: Not graded. No license is recorded for this server.Quality: Not graded. No README or tool list has been captured yet.Maintenance: Not graded. No commit or release date has been recorded.
Portable, user-owned AI memory packs: read, validate, fingerprint, diff, and observe
Registry
–License–Quality–MaintenanceLicense: Not graded. No license is recorded for this server.Quality: Not graded. No README or tool list has been captured yet.Maintenance: Not graded. No commit or release date has been recorded.
One shared memory for every AI you use, in plain Markdown files you own.
Registry
–License–Quality–MaintenanceLicense: Not graded. No license is recorded for this server.Quality: Not graded. No README or tool list has been captured yet.Maintenance: Not graded. No commit or release date has been recorded.
Self-curating agent memory kept honest by survival-based selection over measured outcomes.
Registry
–License–Quality–MaintenanceLicense: Not graded. No license is recorded for this server.Quality: Not graded. No README or tool list has been captured yet.Maintenance: Not graded. No commit or release date has been recorded.
Local-first, auditable memory for MCP-compatible AI agents with explicit writes and SQLite storage.
Registry
–License–Quality–MaintenanceLicense: Not graded. No license is recorded for this server.Quality: Not graded. No README or tool list has been captured yet.Maintenance: Not graded. No commit or release date has been recorded.
Auditable memory for AI agents: provenance, cascade retraction, conflict refusal
Registry
–License–Quality–MaintenanceLicense: Not graded. No license is recorded for this server.Quality: Not graded. No README or tool list has been captured yet.Maintenance: Not graded. No commit or release date has been recorded.
Portable AI memory as MCP tools: five reads and three controlled writes.
Registry
–License–Quality–MaintenanceLicense: Not graded. No license is recorded for this server.Quality: Not graded. No README or tool list has been captured yet.Maintenance: Not graded. No commit or release date has been recorded.
Self-hosted web search for LLM agents: search -> fetch -> rank pipeline with semantic caching
Registry
–License–Quality–MaintenanceLicense: Not graded. No license is recorded for this server.Quality: Not graded. No README or tool list has been captured yet.Maintenance: Not graded. No commit or release date has been recorded.
MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.
Registry
–License–Quality–MaintenanceLicense: Not graded. No license is recorded for this server.Quality: Not graded. No README or tool list has been captured yet.Maintenance: Not graded. No commit or release date has been recorded.
Local-first agent memory over SQLite: remember, recall, link, forget. Degrades, never fails.
Registry
–License–Quality–MaintenanceLicense: Not graded. No license is recorded for this server.Quality: Not graded. No README or tool list has been captured yet.Maintenance: Not graded. No commit or release date has been recorded.
Local-first AI memory over MCP. No account; you own the store.
Registry
–License–Quality–MaintenanceLicense: Not graded. No license is recorded for this server.Quality: Not graded. No README or tool list has been captured yet.Maintenance: Not graded. No commit or release date has been recorded.
RAG memory for LLM agents over Garnet Vector Sets: store text as embeddings, recall by meaning.
Registry
–License–Quality–MaintenanceLicense: Not graded. No license is recorded for this server.Quality: Not graded. No README or tool list has been captured yet.Maintenance: Not graded. No commit or release date has been recorded.
Review gate for shared agent memory: an unreviewed or hand-edited memory is never served.
Registry
–License–Quality–MaintenanceLicense: Not graded. No license is recorded for this server.Quality: Not graded. No README or tool list has been captured yet.Maintenance: Not graded. No commit or release date has been recorded.
On-device, self-organizing memory for AI coding agents — recalls the right facts into each prompt.
Registry
–License–Quality–MaintenanceLicense: Not graded. No license is recorded for this server.Quality: Not graded. No README or tool list has been captured yet.Maintenance: Not graded. No commit or release date has been recorded.
Analyze LLM API costs: token waste detection, caching savings estimates, model comparison
Registry
–License–Quality–MaintenanceLicense: Not graded. No license is recorded for this server.Quality: Not graded. No README or tool list has been captured yet.Maintenance: Not graded. No commit or release date has been recorded.
Clean messy CSVs: an LLM picks the steps, tested code does the work. Data untouched by the model.
Registry
–License–Quality–MaintenanceLicense: Not graded. No license is recorded for this server.Quality: Not graded. No README or tool list has been captured yet.Maintenance: Not graded. No commit or release date has been recorded.
Persistent memory for AI thinking partnerships: hybrid search and a temporal knowledge graph.
Registry
–License–Quality–MaintenanceLicense: Not graded. No license is recorded for this server.Quality: Not graded. No README or tool list has been captured yet.Maintenance: Not graded. No commit or release date has been recorded.
–License–Quality–MaintenanceLicense: Not graded. No license is recorded for this server.Quality: Not graded. No README or tool list has been captured yet.Maintenance: Not graded. No commit or release date has been recorded.
Provenance-first research memory with hash-bound evidence and a fail-closed eligibility gate.
Registry
–License–Quality–MaintenanceLicense: Not graded. No license is recorded for this server.Quality: Not graded. No README or tool list has been captured yet.Maintenance: Not graded. No commit or release date has been recorded.
Self-curating shared memory that keeps your agents working like a high-performing team
Registry
–License–Quality–MaintenanceLicense: Not graded. No license is recorded for this server.Quality: Not graded. No README or tool list has been captured yet.Maintenance: Not graded. No commit or release date has been recorded.
Local-first long-term memory for AI coding agents. Stored on your own machine.
Registry
–LicenseCQuality–MaintenanceLicense: Not graded. No license is recorded for this server.Quality: C. 55/100 for listing completeness. Lost points: short README, 7 of 7 tools barely described, no repository link.Maintenance: Not graded. No commit or release date has been recorded.
Governed, self-hosted memory for AI agents: writes queue until a named person approves.
Registry
–License–Quality–MaintenanceLicense: Not graded. No license is recorded for this server.Quality: Not graded. No README or tool list has been captured yet.Maintenance: Not graded. No commit or release date has been recorded.