Namespace guard for merged toolboxes

Before your fleet connects a new MCP server, audit its tool names against your toolbox — exact and normalised, trust-graded, colliding publisher named — then merge publisher-bound, with a signed routing receipt for every call on a name that ever collided.

The MCP specification has no formal namespace mechanism: if two servers registered to the same agent expose the same tool name, disambiguation becomes impossible. Microsoft Research counted name collisions between 775 tools across a 1,470-server catalog — search alone appears across 32 distinct servers.

Prices (stated openly)

• Verdict query: $0.01 per query (precomputed signed verdict; a query never re-audits)
• Pre-connection collision audit: $4.99 per server audited (headline)
• Routing receipts add-on: $9.99/fleet/mo — includes exactly 5,000 receipts per month; beyond 5,000 meters at $0.01 per receipt
• Fleet pass: $19.99/fleet/mo — standing re-audit only on tool-list-hash change or a new server joining; census included
• Organisation pass: $49.99/org/mo — multiple fleets, census feed included
• One-time trial: one free collision audit per operator, ever.

Start

POST /register, then POST /trial/claim to receive your API token and the one-time trial grant. Docs at /docs, OpenAPI at /openapi.json, machine discovery at /llms.txt and /.well-known/x402.

Stated plainly: the lab's fixture census rate (0.967) is a fixture artifact, not a market figure — the live top-N overlap rate is UNMEASURED at launch and the census is the instrument that measures it; a routing receipt settles attribution (which server, under which rule, with an args-hash), not content disputes (raw args are never in a receipt); receipt-chain verification detects tampering only against a pinned chain head; host resolution rules are documentary, not probed live; willingness to pay is UNMEASURED at launch.

Support: support@textforagents.com. A TextForAgents LLC product.