# epistemic-guard: Signed Tool Receipts & Verification

> epistemic-guard: Signed Tool Receipts & Verification is an open-source MCP server for security. Verifies agent tool claims with Ed25519 receipts and dedupes syndicated RAG sources. It runs locally on your machine and is started by your AI client.

- **Kind:** MCP server
- **Pricing:** Open source
- **Platforms:** CLI, Linux, macOS, Windows, self-hosted
- **Website:** https://rollsolo.app/epistemic-guard
- **Repository:** https://github.com/alienatedaliens/epistemic-guard
- **MCP Registry name:** io.github.AlienatedAliens/epistemic-guard
- **Categories:** [security](https://ai-powered.com/categories/security)
- **Listing updated:** 2026-11-18

## About

The README says the package checks whether an assistant reply describes tool actions that never actually ran, such as a refund that failed or a file that was never written. It does this by comparing the reply against signed receipts that a proxy or decorator records for each tool call, including runtime errors and pre-execution rejections.

The MCP mode runs as a separate process that wraps any stdio MCP server, keeps the signing key out of the child environment, and appends signed entries to a Merkle JSONL log that can be verified from the command line or in CI. A Python mode offers decorators and a supervisor class for checking prose clause by clause, including streamed output. Memory writes can be gated so that only entries signed by user or tool keys are stored in a SQLite provenance store.

It is aimed at developers building MCP servers, tool-calling agents and retrieval pipelines who need post-execution checks rather than input filtering. Neural classifiers are English-only and need an optional model download.

## Features

- **Signed tool receipts:** Records completions, runtime errors and pre-execution rejections as Ed25519-signed entries in an append-only Merkle log.
- **Out-of-process MCP proxy:** Wraps any stdio MCP server in its own process so the signing key is not passed to the wrapped server.
- **Post-execution claim checking:** Compares assistant replies clause by clause against receipts and flags actions that were not executed or failed.
- **Memory write gating:** Stores only entries whose signatures verify against trusted public keys, with append-only SQLite triggers and a hash chain.
- **RAG source deduplication:** Collapses near-duplicate syndicated snippets so repeated wire copy is not counted as independent corroboration.

## Good for

- Catching an agent that claims it sent an email or deleted a file when the tool call failed or never ran
- Auditing signed tool-call logs from an MCP server in CI pipelines
- Preventing unverified assistant prose from being written into long-term vector or SQLite memory
- Counting independent sources before answering medical, legal or security questions from retrieved pages

## Install

### Claude Code (Terminal)

```sh
claude mcp add epistemic-guard -- uvx epistemic-guard
```

### Claude Desktop (claude_desktop_config.json)

```json
{
  "mcpServers": {
    "epistemic-guard": {
      "command": "uvx",
      "args": [
        "epistemic-guard"
      ]
    }
  }
}
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "epistemic-guard": {
      "command": "uvx",
      "args": [
        "epistemic-guard"
      ]
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "epistemic-guard": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "epistemic-guard"
      ]
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "epistemic-guard": {
      "command": "uvx",
      "args": [
        "epistemic-guard"
      ]
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "epistemic-guard": {
      "command": "uvx",
      "args": [
        "epistemic-guard"
      ]
    }
  }
}
```

## Tools

- `verify_narration`: Verifies an assistant reply against receipts.
- `verify_receipt_log`: Verifies a signed receipt log.
- `inspect_receipt`: Inspects a single receipt.
- `corroborate_sources`: Collapses duplicate sources and counts independent corroboration.

## FAQ

### Does it replace pre-execution guardrails?

No. The README positions it as a complement to input and tool-call firewalls such as NeMo Guardrails, checking output and memory writes after execution.

### How is it installed?

The README gives pip install epistemic-guard, with an optional epistemic-guard download-models step for the INT8 neural weights.

### Does it make LLM API calls?

The README states it runs locally with zero LLM API calls.

### What languages do the neural classifiers support?

The README says the neural classifiers are English-only.

### Is epistemic-guard: Signed Tool Receipts & Verification free?

Yes. epistemic-guard: Signed Tool Receipts & Verification is open source, so you can use and self-host it for free.

### How do I add epistemic-guard: Signed Tool Receipts & Verification to Claude Code?

Run this command in your terminal: claude mcp add epistemic-guard -- uvx epistemic-guard

### What are the best alternatives to epistemic-guard: Signed Tool Receipts & Verification?

The closest alternatives to epistemic-guard: Signed Tool Receipts & Verification are Aga MCP Server, AgentProof, Protect MCP, Provared MCP executor and N0N4 Guardian.

## Where this comes from

- Description: written from the project's README, the project's website and its MCP Registry entry.
- Install steps: from the official MCP Registry entry.

## Alternatives

- [Aga MCP Server](https://ai-powered.com/mcp/aga-mcp-server): Aga MCP Server is an open-source MCP server for security.
- [AgentProof](https://ai-powered.com/mcp/agentproof-2): AgentProof is an open-source MCP server for security.
- [Protect MCP](https://ai-powered.com/mcp/protect-mcp): Protect MCP is an open-source MCP server for security.
- [Provared MCP executor](https://ai-powered.com/mcp/provared-mcp-executor): Provared MCP executor is a free MCP server for security.
- [N0N4 Guardian](https://ai-powered.com/mcp/n0n4-guardian): N0N4 Guardian is a paid MCP server for security.
- [Emilia Protocol](https://ai-powered.com/mcp/emilia-protocol): Emilia Protocol is an open-source MCP server for security.
- [Verfy](https://ai-powered.com/mcp/verfy): Verfy is an open-source MCP server for security.
- [mcp-agent-template](https://ai-powered.com/mcp/mcp-agent-template): mcp-agent-template is an open-source MCP server for security.

---
Source: https://ai-powered.com/mcp/epistemic-guard-signed-tool-receipts-and-verification
