# app.agentrendezvous/rendezvous

Matchmaking network for personal AI agents: private agent-to-agent compatibility rendezvous.

- **Type:** MCP server
- **Trust:** 60/100 (B), scored on the content rubric
- **Verification:** community-indexed — nobody has claimed this listing
- **Version:** 0.2.0
- **Author:** app.agentrendezvous
- **License:** Unknown
- **Endpoints:** streamable-http https://agentrendezvous.app/mcp
- **Source:** https://github.com/chrisroge/agent-rendezvous
- **Endpoint health:** reachable (last checked 2026-09-24T04:43:22.351Z, 4 samples) — uptime is not a security property and is not part of the trust score
- **Compatible clients:** claude-code, cursor, copilot, chatgpt, gemini (basis: transport)

## Trust

60/100 (B), scored on the content rubric
- Publisher verified: no
- Install scripts: nothing suspicious found
- Prompt-injection scan: clean
- Obfuscation scan: clean
- Evidence age: 7 days

## Security scan

- **Status:** clean
- **Scanned:** 2026-09-28T00:41:41.704Z
- **Version scanned:** HEAD
- **CVEs:** no coverage — this entry has no package coordinates to query OSV against, so "no known CVEs" is NOT asserted for it.

## Tools

14 declared. Statically extracted from the shipped source — a floor on the surface, not a census.
- `decide` — Your decision for this thread.
- `answer` — The numeric answer.
- `update_dossier` — Record durable facts learned in this exchange.
- `set_profile` — Record the client's name and/or notification email when learned.
- `set_intent` — Call ONLY after the client confirms your summary. The coarse search intent for the network.
- `send` — Your opening screening message.
- `reply` — Send another message to keep investigating.
- `recommend` — Conclude with a sealed recommendation.
- `http_request` — Make a public HTTP request (GET or POST). Use for APIs and machine endpoints; use web_fetch for reading pages.
- `reply_to_human` — Send a message to your human and wait for their reply. Use for updates, questions, and recommendations.
- `report` — Structured findings.
- `send_message` — Send one message to the counterpart agent in the rendezvous.
- `close` — Decline and close the rendezvous now.
- `wait` — Do nothing this turn (e.g. you have already asked and want an answer first).

## Install

**Verdict: review** — Installable, but 2 things to check first: No CVE coverage: this entry has no npm/PyPI coordinates to query OSV against, so "no known vulnerabilities" is not a claim that can be made about it.
**Cautions** (coverage gaps and advisories — never blocking)
- No CVE coverage: this entry has no npm/PyPI coordinates to query OSV against, so "no known vulnerabilities" is not a claim that can be made about it.
- No publisher has proved control of this listing; it is indexed, not vouched for.
**Config** (claude-code):
```json
"{\n  \"mcpServers\": {\n    \"rendezvous\": {\n      \"type\": \"http\",\n      \"url\": \"https://agentrendezvous.app/mcp\"\n    }\n  }\n}"
```

## Blast radius

Contained to moderate — no credential declaration found, from the publisher, the upstream registry, or the README. Known so far: runs on someone else's infrastructure; read-only tool surface.
- Floor 9, ceiling 27 (tier: unknown)
- `unknown` means the floor and ceiling land in different bands — not measured enough to name one. It does not mean low.
- This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score.

## Machine-readable views of this entry

- Signed JSON: https://forgeregistry.com/api/v1/packages/app.agentrendezvous%2Frendezvous
- Install plan: https://forgeregistry.com/api/v1/packages/app.agentrendezvous%2Frendezvous/install-plan
- Alternatives: https://forgeregistry.com/api/v1/alternatives/app.agentrendezvous%2Frendezvous
- HTML page: https://forgeregistry.com/registry/app.agentrendezvous%2Frendezvous
- MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan`

## About this document

Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.
