Census and digest-verify a remote MCP server's loadable skills per host persona.
Scored across 2 tools
The two tools have clearly separate roles: one is static informational lookup and the other is a yes/no verification of a digest against a receipt. There is little risk of confusion, though 'census_info' is vague enough that its boundary depends entirely on the description.
The names mix conventions: 'census_info' is a noun/domain label while 'check_approval' is a verb_noun action. With only two tools the pattern is readable but not predictable for a caller guessing the naming scheme.
Two tools is thin for a server framed as 'census verification'; the surface feels like a slice of a larger API. It is defensible if the scope is deliberately narrow, but it sits at the borderline of under-scoped.
There is no way to discover receipts, list skills, or enumerate census entries, so an agent must arrive already knowing a receipt_id, skill_uri, and digest. Info plus a single check covers a minimal lifecycle but leaves obvious discovery gaps.
Product, prices, cap and limits.
Inputs: no named parameters.
Is this digest the approved one for a skill on one of your receipts? Args: token, receipt_id, skill_uri, digest.
Inputs: token (required), digest (required), skill_uri (required), receipt_id (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Combined Server-Surface Census: identity, tool contract + skill digests in one signed snapshot.
Pre-install canonical-identity verification for MCP servers and skills, with signed verdicts.
Score any remote MCP server for Claude, ChatGPT, Gemini and MCP Registry readiness.
Search MCP servers and agent skills, read their checks, and get install config for your client.
Add one secure layer between your agents and this server.