# inspeximus: agent memory with provenance, GDPR erasure and a tamper-evident audit trail (io.github.DanceNitra/inspeximus@2.27.4) > Source: > Published: 2026-09-13 14:16:09+00:00 [← Index](/leaderboard) # inspeximus: agent memory with provenance, GDPR erasure and a tamper-evident audit trail Self-correcting agent memory: recall, supersede, revert, forget, GDPR erasure, audit receipts. The current version, v2.27.4, was published to the official MCP registry on 2026-09-13. It is distributed as inspeximus 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](/stats) put this record in context. ## Using inspeximus: agent memory with provenance, GDPR erasure and a tamper-evident audit trail 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-wire ``` [method](/methodology) Semantic screen found no manipulation pattern in the description. Conformance probe not yet run. `mcpindex.integrity.description` passINFO evidence“No malicious instructions”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 - - 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 →](/screen) ## That verdict was true at screening time (snapshot 2026-09-13). Contracts can change after screening, with no version bump. The gate pins inspeximus: agent memory with provenance, GDPR erasure and a tamper-evident audit trail’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 →](/guides/install-the-gate-first-hold) Related: [how to trust an MCP server](/guides/how-to-trust-an-mcp-server) · [screen before install](/guides/screen-mcp-server-before-install) · [silent contract drift](/guides/mcp-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 inspeximus: agent memory with provenance, GDPR erasure and a tamper-evident audit trail](https://mcpindex.ai/server/io-github-dancenitra-inspeximus) - screening verdict, registry provenance, and contract drift monitoring. Independent trust record for inspeximus: agent memory with provenance, GDPR erasure and a tamper-evident audit trail - 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. ``` [![mcpindex](https://mcpindex.ai/api/v1/badge/io-github-dancenitra-inspeximus)](https://mcpindex.ai/server/io-github-dancenitra-inspeximus) mcpindex verdict ``` `INSPEXIMUS_PATH` Path to the JSON memory file the server persists to (defaults to ./inspeximus_memory.json). `INSPEXIMUS_ECHO_GUARD` 1 (default) blocks a restated retired value from resurrecting a corrected fact; 0 = legacy keyed supersession. `INSPEXIMUS_EMBED_URL` Optional OpenAI-compatible /embeddings endpoint for SEMANTIC recall (e.g. http://localhost:11434/v1/embeddings for local Ollama). Unset = deterministic lexical recall. `INSPEXIMUS_EMBED_MODEL` Embedding model id used with INSPEXIMUS_EMBED_URL (default: text-embedding-3-small; for Ollama use e.g. nomic-embed-text). [methodology](/methodology) [Fodda Knowledge Graphsai.fodda/mcp-server](/server/ai-fodda-mcp-server) Expert-curated knowledge, brand, research & earnings intelligence — 47 tools, 220+ graphs. [Achriomcom.achriom/achriom](/server/com-achriom-achriom) Media memory for AI agents and their humans: books, movies, music, shows, anime, podcasts, games. [io.github.DanceNitra/mnemoio.github.DanceNitra/mnemo](/server/io-github-dancenitra-mnemo) Self-correcting agent memory + MCP server: recall, supersede/revert/review corrections, erasure.