toolcallwitness-mcp — Claude Code MCP server: tool-call receipts
A hosted MCP server that records what an agent called: receipts, approval checks, risk summaries and audit exports. Useful when you have to show which tool ran.
claude mcp add --transport http toolcallwitness-mcp https://toolcallwitness.clauxel.com/mcpWhat toolcallwitness-mcp does
Four tools ship with it: create_witness_receipt, check_approval_rule, summarize_risk_timeline and export_audit_receipt. One writes a receipt for a call, one tests an approval rule, one builds a timeline of risk, one exports a receipt for review. Arguments get redacted along the way and results are condensed into short summaries.
This is a paid remote server, not something you run locally. It speaks Streamable HTTP, so your client has to handle remote servers of that kind. Production traffic needs a bearer token obtained from the product site, passed as Authorization: Bearer <token>. Hitting /mcp in a browser without credentials returns a JSON error rather than internal detail.
Setup is four steps: pick a plan on the site, get or request an API token, point your MCP client at https://toolcallwitness.clauxel.com/mcp, then send JSON-RPC with the token. The repository holds public documentation only — the production source is not there, so you cannot audit the service locally.
What it helps with
- record which tool an agent invoked and with what arguments
- get evidence that a risky call was approved
- keep sensitive arguments out of the call log
- build a timeline of risk across several calls
- export receipts for review or audit
Example prompts for the agent
- Create a receipt for the last tool call with
create_witness_receipt - Run
check_approval_ruleto see whether this call needs approval - Summarize risk for the session with
summarize_risk_timeline, then export it viaexport_audit_receipt
How to install toolcallwitness-mcp
Platform CLI: remote server
claude mcp add --transport http toolcallwitness-mcp https://toolcallwitness.clauxel.com/mcpPlatform CLI: remote server
codex mcp add toolcallwitness-mcp --url https://toolcallwitness.clauxel.com/mcpConfig file
{
"mcpServers": {
"toolcallwitness-mcp": {
"url": "https://toolcallwitness.clauxel.com/mcp"
}
}
}Config file
{
"servers": {
"toolcallwitness-mcp": {
"type": "http",
"url": "https://toolcallwitness.clauxel.com/mcp"
}
}
}Platform CLI: remote server
gemini mcp add -t http toolcallwitness-mcp https://toolcallwitness.clauxel.com/mcpStep by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about toolcallwitness-mcp
How do I install toolcallwitness-mcp in Claude Code?
Run claude mcp add --transport http toolcallwitness-mcp https://toolcallwitness.clauxel.com/mcp. Requests still need a bearer token afterwards.
What does toolcallwitness-mcp do?
It keeps a record of agent tool calls: writing receipts, checking approval rules, summarizing risk and exporting receipts for audit.
Do I need a token to use it?
Yes. It is a paid hosted service, and the token comes from the product site. Without it, production requests to /mcp fail.
