inspeximus: agent memory with provenance, GDPR erasure and a tamper-evident audit trail MCP Server
io.github.DanceNitra/inspeximus
What this kind of tool is for
- Hand your agent a structured way to call a model or an inference API.
- Compare outputs from two different providers on the same prompt.
- Wire retrieval, embeddings, or generation into an existing agent workflow.
How to compare servers like this
- Provider coverage:
- Match the tool's supported providers and models to the ones your project uses.
- Cost exposure:
- Model-backed tools spend real API budget; check how usage and limits are configured.
- Maintenance signal:
- The provider landscape shifts weekly; prefer tools updated within the last few months.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the inspeximus: agent memory with provenance, GDPR erasure and a tamper-evident audit trail MCP server?
Self-correcting agent memory: recall, supersede, revert, forget, GDPR erasure, audit receipts.
How to install inspeximus: agent memory with provenance, GDPR erasure and a tamper-evident audit trail
Copy-paste configuration for popular MCP clients.
INSPEXIMUS_PATHPath to the JSON memory file the server persists to (defaults to ./inspeximus_memory.json).
INSPEXIMUS_ECHO_GUARD1 (default) blocks a restated retired value from resurrecting a corrected fact; 0 = legacy keyed supersession.
INSPEXIMUS_EMBED_URLOptional OpenAI-compatible /embeddings endpoint for SEMANTIC recall (e.g. http://localhost:11434/v1/embeddings for local Ollama). Unset = deterministic lexical recall.
INSPEXIMUS_EMBED_MODELEmbedding model id used with INSPEXIMUS_EMBED_URL (default: text-embedding-3-small; for Ollama use e.g. nomic-embed-text).
{
"mcpServers": {
"inspeximus": {
"command": "uvx",
"args": [
"inspeximus",
"--from",
"inspeximus[mcp]",
"mcp"
],
"env": {
"INSPEXIMUS_PATH": "<YOUR_INSPEXIMUS_PATH>",
"INSPEXIMUS_ECHO_GUARD": "<YOUR_INSPEXIMUS_ECHO_GUARD>",
"INSPEXIMUS_EMBED_URL": "<YOUR_INSPEXIMUS_EMBED_URL>",
"INSPEXIMUS_EMBED_MODEL": "<YOUR_INSPEXIMUS_EMBED_MODEL>"
}
}
}
}Related MCP servers

Self-correcting agent memory + MCP server: recall, supersede/revert/review corrections, erasure.
Live pricing data for AI models across vendors: input/output prices per 1k tokens as JSON.

Eight metered machine-intelligence tools for AI agents with native x402 payment paths.
LocalPlate MCP for verified restaurant nutrition, food search, diary logs, and Plato guidance.

Local semantic search and graph analysis for your codebase—give AI agents the right context without leaving your machine.

