mcpField
T
toolcallwitness-mcp

toolcallwitness-mcp

Remote
github.com/clauxelAI & Agents0Updated 23w ago
Repository

About toolcallwitness-mcp

toolcallwitness-mcp is a hosted remote MCP for recording AI agent tool-call evidence and supporting review. It provides receipts, approval checks, risk summaries, and audit exports.

Key features

  1. 01Tool-call receipt creation
  2. 02Approval-rule checks
  3. 03Risk timeline summaries
  4. 04Audit receipt exports
  5. 05Argument redaction and result summaries

Use cases

  1. 01Recording evidence for agent tool calls
  2. 02Checking whether a call meets approval rules
  3. 03Reviewing risk timelines
  4. 04Exporting audit records

MCP support

Exposes tools to MCP clients over a Streamable HTTP remote endpoint. Production requests require a bearer token.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://toolcallwitness.clauxel.com/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

All endpoints
Streamable HTTPhttps://toolcallwitness.clauxel.com/mcpAuth required

Tools

Details

From the project README

ToolCall Witness MCP

A witness layer for AI agent tool calls.

Paid remote MCP for agent tool-call receipts, approval evidence, arguments redaction, result summaries, and review exports.

Public Endpoints

Access

This is a paid hosted remote MCP. Production calls require a bearer token issued from the product website.

Authorization: Bearer <token>

Unauthenticated browser visits to /mcp return a clear JSON error instead of internal details.

Tools

  • create_witness_receipt
  • check_approval_rule
  • summarize_risk_timeline
  • export_audit_receipt

Quick Start

  1. Open the website and choose a plan.
  2. Create or request an API token.
  3. Add the endpoint to an MCP client that supports Streamable HTTP remote servers.
  4. Send JSON-RPC requests with the bearer token.

Useful Links

Related Workflow

  • OpenHuman Online is useful when this MCP rollout also needs human-readable source memory, meeting notes, or approval context outside the server.

Status

This repository is a public documentation and directory-submission reference for the hosted service. It does not contain the private production source code.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.