Q
Which clients work?
Any MCP-compatible client: Claude Code, Cursor, Codex CLI, Windsurf, Gemini CLI, OpenCode. The protocol is identical; only the config location differs per client.
Docs · MCP Setup (Claude Code, Cursor, …)
MCP Setup (Claude Code, Cursor, …).
One memory, every harness.
Direct answer
mind-mcp serves your local graph to any MCP client over stdio: 8 tools, budgeted queries (default 4096 tokens), zero accounts. Five lines of .mcp.json in your project root, restart the client, and Claude Code, Cursor, or Codex CLI reads and writes the same memory Anvaya CLI uses natively.
MCP Setup (Claude Code, Cursor, …)
Steps
011 · Start the daemonMind runs as a Unix-socket daemon (auto-spawn on first client connect). Verify with anv mind stats.
022 · Add .mcp.jsonFive lines in project root naming the mind-mcp server over stdio. Same file shape every MCP client expects.
033 · Restart the clientReload Claude Code / Cursor / Codex so it picks up the server. Expect 8 tools: mind_query, mind_search, mind_get_node, mind_record_change, mind_stats, session start/end, mind_get_threads.
044 · Query with budgetmind_query takes natural language plus token_budget (4096 default) and returns PackedContext — critical nodes, patterns, fixes, concepts.
055 · Record outcomesAgents should call mind_record_change on decisions and fixes so future sessions — any client — inherit the lesson.
Questions
Asked About MCP Setup (Claude Code, Cursor, …).
Q
Latency vs native?
MCP ~10ms per call vs Direct <0.5ms / IPC ~2ms inside Anvaya CLI. Irrelevant next to model latency; the bridge tax is noise.
Q
Does MCP send code anywhere?
No — stdio to your local daemon. Cloud exposure depends only on which LLM provider your agent itself uses.
Stop Starting From Zero.
One binary. 11+9 Rust crates. 545 tests. Hand-written HNSW index. Three transport modes. Four providers, Ollama, Anthropic, OpenAI, Siemens. Zero API keys required to start. Mind remembers everything after the first session.