MCP server

Recall

io.github.mcp-dir/recall-mcp

Checked 26 Oct 2026, 08:29 UTC · Connected to it and listed its tools

Recall (recall.it) — your AI knowledge base / 'second brain'. Via the official API: semantic search

Source

At a glance

Type

MCP server

Publisher

Not verified

Status

Working at last check

Tools

10

Token cost

About 1,973 tokens per request

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

26 Oct 2026, 08:29 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

claude mcp add --transport http recall-mcp https://api.mcp.ai/p_recall

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.recall-mcp]
url = "https://api.mcp.ai/p_recall"

Gemini CLI

{"mcpServers":{"recall-mcp":{"httpUrl":"https://api.mcp.ai/p_recall"}}}

Cursor

{"mcpServers":{"recall-mcp":{"url":"https://api.mcp.ai/p_recall"}}}

VS Code

{"servers":{"recall-mcp":{"type":"http","url":"https://api.mcp.ai/p_recall"}}}

Antigravity

agy mcp add recall-mcp https://api.mcp.ai/p_recall

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"recall-mcp","server_url":"https://api.mcp.ai/p_recall","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"recall-mcp","server_url":"https://api.mcp.ai/p_recall"}

Tools

• recall_get_card ~154 tokens
  Conteúdo de um card específico (chunks). Use focus_query pra focar quais trechos voltam e max_chunks (1-50, default 20) pra limitar o volume. Bulk support: accepts card_ids for batched execution.
• recall_list_accounts ~68 tokens
  Lista contas Recall vinculadas a este install — id e apelido.
• recall_list_cards ~144 tokens
  Lista os cards da sua base Recall (leitura). Filtros opcionais: tags (UUIDs), intervalo de datas (date_from/date_to, ISO 8601) e source_url_contains. Sem filtros, retorna seus cards.
• recall_search ~224 tokens
  Busca semântica na sua base Recall. `q` é a consulta em linguagem natural. mode: focused (rápido, menos resultados, default) ou exhaustive (cobertura maior). Filtros opcionais: card_id, tags, intervalo de datas, source_url_contains. Bulk support: accepts card_ids for batched execution.

Browse

• GitHub tools
• Notes and wikis
• GitHub and code hosting
• Searching your documents (RAG)

Related MCP servers

• INITE Brain
  Long-term memory for AI agents: a bitemporal knowledge graph with cited answers.
• StackFast FractWin Expert Brain
  Expert knowledge base for sales, negotiation, strategy, operations, and risk.
• Neuron
  AI-powered WhatsApp chatbot platform with 196 tools for bots, campaigns, and contacts.
• Call2Me
  Place real phone calls, read transcripts, run a live interpreter and buy numbers.
• Meeba Brain
  Repository knowledge graph MCP server for codebase understanding and debugging.
• Blobpedia
  Celestia knowledge base: CIPs, docs, forum, videos, GitHub, plus live on-chain state
• SingChat
  Free live chat and AI support agent. Auto-create a workspace and embed from your AI editor.
• Mazza Group AI APIs
  21 AI APIs pay-per-call with USDC on Base via x402. No keys, no signup.

Badge for your README

[![AptLynx](https://aptlynx.net/badge/io.github.mcp-dir/recall-mcp.svg)](https://aptlynx.net/servers/io.github.mcp-dir/recall-mcp)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents