Verified doc corpora for agents: grep-first retrieval, hashed pages, Merkle+RFC-3161 receipts
Glama couldn't complete the latest health check. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
Scored across 13 tools
Each tool targets a distinct aspect: reading different content types (fetch, read_md, read_facts), searching (search, grep_corpus, glob_corpus), listing (list_dir, list_indexes), diffs and changelog (diff_md, changed_since), proofs (prove), metadata query (query_manifest), and status (snapshot_status). No overlap.
Most tools follow a verb_noun pattern (e.g., list_dir, read_md, grep_corpus). A few are single verbs (fetch, search, prove) but still clear. The naming is largely consistent with minor deviations.
13 tools cover the read-only library domain well: reading, searching, listing, diffing, proving, and status. The scope is well-defined without unnecessary tools.
The tool set is quite complete for a read-only library, offering multiple access patterns (by path, ID, pattern, search, changes). Missing are tools to list snapshots or get full corpus structure, but these are minor gaps.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
changed_sincediff_mdfetchglob_corpusgrep_corpuslist_dirlist_indexesprovequery_manifestread_factsread_mdsearchsnapshot_statusLocal-first long-term memory for AI agents, with byte-recomputable signed verification receipts.
Verifiable provenance for AI agents — ZK proofs over confidential documents, no plaintext exposure.
Token-efficient search for coding agents over public and private documentation.
Deterministic fact verification for AI agents — checksums & curated data, not guesses.
Add one secure layer between your agents and this server.
