RAWThink
Persistent memory for AI thinking partnerships: hybrid search and a temporal knowledge graph.
Open the source (opens github.com) https://github.com/ygtalp/rawthink-mcp
Before you use it
- Runs on your computer with your permissions. Read what it can do before connecting it to an agent.
What it is
MCP servers from io.github.ygtalp.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
pypi package (stdio)
rawthink-mcp@2.0.1
From the server's entry in the official MCP Registry
Settings it asks for
RAWTHINK_VAULT· Path to the vault directory holding sessions, qnotes and the knowledge graph.MEMORY_FILE_PATH· Path to memory.jsonl. Defaults to <vault>/memory.jsonl.QDRANT_URL· Qdrant server URL.QDRANT_PATH· Set to a directory to run Qdrant embedded instead of via Docker.OLLAMA_URL· Ollama server URL. Without it, retrieval degrades to sparse-only.OLLAMA_MODEL· Embedding model. Changing it requires a full reindex.RAWTHINK_TOOL_PROFILE· Which tools to expose: recall (4, read-only), record (5, the write path), or full (17).RAWTHINK_BM25_STATE· Path to the BM25 state file. Defaults to <vault>/.bm25_state.json.RAWTHINK_LOG_LEVEL· Log level for diagnostics on stderr.
Related
-
GitHub MCP server
MCP serversGitHub's official MCP server. It lets an agent read and work with repositories, issues and pull requests.
https://api.githubcopilot.com/mcp/ -
Apify MCP server
MCP serversLets an agent run Apify's ready-made scrapers to pull data from websites, search engines, maps and social platforms.
-
Official MCP Registry
MCP serversThe MCP project's own registry of public MCP servers, so you can look for a connector before building one.
-
MCP reference servers
MCP serversSmall example servers from the MCP project (filesystem, git, fetch, memory and more) that show how MCP works.
-
Connect MCP servers to Claude Code
MCP serversAnthropic's guide to adding MCP servers to Claude Code, with examples of local and remote servers.
-
Playwright MCP
MCP serversLets an agent drive a real browser: open pages, click, fill in forms and read what's on screen.
claude mcp add playwright npx @playwright/mcp@latest