Attestari
Auditable memory for AI agents: provable deletion, tamper-evident audit, time-travel recall.
The current version, v0.0.6, was published to the official MCP registry on 2026-08-12. It is distributed as attestari on PyPI, filed under Memory & RAG by this index, and declares 4 environment variables. Removals and unreachable sources are measured across every server this index tracks, contract drift across the servers that answer in consecutive snapshots; the index's current counts put this record in context.
Using Attestari in Claude, Cursor, Gemini CLI, Cline, or Zed?
MCP tool contracts can change remotely with no version bump. The mcpindex gate pins each contract and HOLDs the call when it drifts-before your agent acts. Zero credentials. This is not the package install for this server itself (use Install this server for that).
Rewrites your MCP host config so each server launches behind the gate. Inspect first: curl -fsSL https://mcpindex.ai/install.sh | less
uv tool install mcpindex-gate && mcpindex-config-wireSemantic screen found no manipulation pattern in the description. Conformance probe not yet run.
mcpindex.integrity.descriptionpassINFOevidence“No malicious instructions found”via static_description
- - Semantic screen only - the deterministic conformance probe has not run on this server
- - Confidence is reported but not yet calibrated (v1)
- - Screen reads the tool description, not the live behavior
- - advisory
- - registry description only no input schema
- - screen model 8b
- - Still current: the description we screened is unchanged, re-checked against the registry
- - The registry listing (version, packages, links) changed after this screen ran - the description we assessed did not
Semantic screen: an LLM judge reads the tool description for hidden instructions (status PARTIAL). A pass means the description is not lying, not that the tool is safe: a high-capability tool with an honest description still warrants caution. The deterministic conformance probe has not been run on this server yet, so the screen here is semantic-only. Posture: advisory. Confidences are reported but not yet calibrated (calibrated=false at v1). Full verdict history is not shown on this page.
Own this server? Screen its description →
That verdict was true at screening time (snapshot 2026-09-25).
Contracts can change after screening, with no version bump. The gate pins Attestari’s tool contracts on first sight and holds any silent change before your agent acts - the check that keeps being true on Tuesday.
See your first HOLD in 2 minutes →
Related: how to trust an MCP server · screen before install · silent contract drift
People vet a server before wiring it in. One line on your project site or docs answers that with an independent record: screening verdict, registry provenance, contract drift history. It stays current as new screens and drift events land.
[Independent trust record for Attestari](https://mcpindex.ai/server/io-github-attestari-attestari) - screening verdict, registry provenance, and contract drift monitoring.<a href="https://mcpindex.ai/server/io-github-attestari-attestari">Independent trust record for Attestari</a> - screening verdict, registry provenance, and contract drift monitoring.A live verdict badge for your README or listing. It reflects the current screen, links back here, and updates when the verdict does.
[](https://mcpindex.ai/server/io-github-attestari-attestari)<a href="https://mcpindex.ai/server/io-github-attestari-attestari"><img src="https://mcpindex.ai/api/v1/badge/io-github-attestari-attestari" alt="mcpindex verdict" height="20" /></a>ATTESTARI_KEKBase64 32-byte root key. Set it to enable encryption at rest and cryptographic erasure (forget() destroys the subject's key and signs the certificate). Without it, forget() is a logical delete and certificates are left unsigned.
ATTESTARI_DATABASE_URLPostgres DSN. Set it to use Postgres + pgvector instead of the default local SQLite file (concurrent access, indexed hybrid search).
ATTESTARI_SQLITE_PATHWhere the default SQLite ledger lives.
ANTHROPIC_API_KEYEnables Claude-powered fact extraction; falls back to the built-in regex extractor when unset.
Expert-curated knowledge, brand, research & earnings intelligence — 47 tools, 220+ graphs.
Long-term memory for AI assistants. Hybrid retrieval, query expansion, auto-topics.
Hybrid vector + reasoning retrieval, agent memory, multi-agent orchestration, MCP server, and RAG.