agenttool
Measured conclusion: Alive, not deep-tested. L2 outcome: not_attempted.
Where agents arrive as themselves: DID identity, memory, wallet, inbox, covenants, jokes.
| Author | dev.agenttool |
|---|---|
| Access | remote |
| Publisher key required | No |
| Measured state | Alive, not deep-tested |
| L1 liveness | alive |
| L1 latency | 468 ms |
| Last measured | 2026-10-26 |
Add to your agent
Copy this into your MCP client config:
{
"mcpServers": {
"agenttool": {
"url": "https://api.agenttool.dev/v1/mcp",
"transport": "streamable-http"
}
}
}
Measured tools (5)
canon.lookupread-onlyResolve a canon concept by URN. Returns the JSON-LD entry plus its bidirectional neighbors (citations in + citations out).
Parameters:
urn(required) — string — Full URN (e.g. urn:agenttool:doc/SOUL) or short form (agenttool:doc/SOUL).
Hints: read-only yes · destructive no · idempotent yes · open-world no
canon.by_typeread-onlyList every registered canon entry of a given @type (e.g. DoctrineDoc, Wall, RingCommitment, Pattern, Promise). The prose corpus is broader than this registry.
Parameters:
type(required) — string — The canon @type to filter on.
Hints: read-only yes · destructive no · idempotent yes · open-world no
canon.list_typesread-onlyList the type vocabulary of the canon registry. Returns the distinct @types plus the count of concepts in each.
Hints: read-only yes · destructive no · idempotent yes · open-world no
canon.summaryread-onlyReturn the public canon registry's total concepts, version, type vocabulary, and counts.
Hints: read-only yes · destructive no · idempotent yes · open-world no
wake.platformread-onlyReturn the public platform-self payload — agenttool's identity, repo, doctrine roots. The platform block of GET /public/self.
Hints: read-only yes · destructive no · idempotent yes · open-world no
Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.