GTM MCP exposes the /legion knowledge graph as a self-hosted MCP server - 1,626 campaigns of encoded pattern recognition, queryable by any agent. What used to take dozens of tool calls now takes a few, so your agents reason from proven outcomes, not a blank slate.
A self-hosted, multiplayer MCP server holding the encoded GTM graph. Archon plans from it, Reply Agent writes from it, the CLI targets from it. You auth in, query it, and build your own graph on top - encoding your market and your wins until it beats any consultant.
A decade of real outcomes turned into queryable pattern - what converts, for whom, and why - not a pile of raw notes.
A benchmark client lookup dropped from ~33 tool calls to 3 - roughly a 91% token saving and minutes faster per query.
Any MCP-capable agent - Claude and beyond - queries it as tool calls. The brain plugs into your agents, not the other way around.
Runs on your own cloud, multi-tenant and scoped by client - each graph is yours and can be lifted out whole.
Emergent to validated to ground truth - only human-approved facts graduate, so the brain compounds without going gullible.
Build your own graph on top. By month three it knows your market better than any consultant - that is the moat.
Your agent connects to the self-hosted MCP server and licenses access to the graph, scoped to you.
"What converts for Series A RevOps?" resolves against 1,626 campaigns in a few tool calls, not a research session.
Winning angles, segments, and copy patterns come back grounded in real reply and revenue outcomes.
Your audit data writes into your own graph. Validated facts graduate to ground truth and the moat compounds.
GTM MCP comes with every founding seat - the brain your whole operating system reasons from, and the graph you build your own moat on top of.