tekmerdb-mcp is a Model Context Protocol server that bridges any MCP-compatible AI agent straight to the engine's HTTP API — the agent inserts facts, searches, and checks source reliability through normal tool calls, in plain language, with no API key and no cloud.
tekmerdb-mcp ships in the same release tarball as the engine — Install already put it at /opt/tekmerdb/tekmerdb-mcp and enabled a tekmerdb-mcp.service systemd unit for it. There's no separate download or install step.
ls /opt/tekmerdb/tekmerdb-mcp systemctl status tekmerdb-mcp
Every mode talks to the engine at a hardcoded http://localhost:3000 — unlike tekmerdb-ingest, the MCP server must always run on the same machine as the engine. What changes between modes is how the agent reaches the MCP server itself.
| Mode | Started with | Use case | Reachable from |
|---|---|---|---|
| stdio | tekmerdb-mcp (default, no flag) |
Claude Desktop and other agents that spawn the binary as a local subprocess | The same machine only — there's no network listener |
| SSE | tekmerdb-mcp --sse |
Network-connected agents, remote clients, multi-user setups | Any machine that can reach mcp_host:mcp_port (see Configure) |
Add this to Claude Desktop's MCP server config:
{
"mcpServers": {
"tekmerdb": {
"command": "/opt/tekmerdb/tekmerdb-mcp"
}
}
}
Restart Claude Desktop. The agent now has insert_pfo, search, get_pfo, get_source, register_source, and update_confidence available as tools.
sudo systemctl start tekmerdb-mcp # or, run directly: /opt/tekmerdb/tekmerdb-mcp --sse
Point the remote MCP client at:
http://<server-ip>:<mcp_port>/sse
mcp_host defaults to 0.0.0.0 — reachable from the network out of the box — and SSE mode has no authentication. Only run it behind a firewall or on a trusted network.
| Tool | What it does |
|---|---|
insert_pfo | Insert a new claim, with confidence and source. The source is registered automatically if it's new. |
search | Semantic search for existing claims by natural-language query. |
get_pfo | Retrieve a specific claim by its UUID. |
get_source | Look up a source's reliability — effective weight, corroboration count, conflict count. |
register_source | Register a new source ahead of time. Idempotent. |
update_confidence | Manually adjust a claim's confidence, with a documented reason for the audit trail. |
Without a memory layer, an agent either re-reads entire source documents every session or trusts everything a RAG pipeline hands back with equal weight — both cost context window and both waste reasoning on things already settled.
insert_pfo once when a fact is found; every future session calls search and gets it back instantly, instead of re-ingesting and re-reasoning over the same source material.search returns only the k most relevant claims, not whole documents — fewer tokens spent per turn than stuffing raw retrieved text into the prompt.get_source lets the agent check a source's track record before leaning on it, instead of treating every retrieved snippet as equally credible.update_confidence lets the agent revise what it believes as new evidence arrives, with the reason captured for audit — instead of silently contradicting itself across sessions.