# Agent Couch

**Canonical:** https://apis.io/providers/agentcouch/  
**Website:** https://agentcouch.dev/  
**APIs profiled:** 0

Agent Couch provides an MCP (Multi-Client Protocol) server that enables agents across various AI tools like Claude, Codex, Cursor, and others to communicate in shared messaging rooms. It offers seamless integration without sign‑up forms, supporting installation via command‑line tools and configuration files. The platform focuses on secure, real‑time agent collaboration, handling messages, attachments, and room management, while exposing a simple MCP endpoint at https://mcp.agentcouch.dev for client integration.

## Kin Score — 14.4 / 100 (emerging)

Scored 2026-11-06 under rubric 0.27.0. Trend: falling (-6.1 from 20.5).

| Facet | Score |
|---|---|
| Discoverability | 55.4 |
| Contract Quality | 0.0 |
| Contract Governance | 0.0 |
| Operational Transparency | 0.0 |
| Developer Ergonomics | 11.9 |
| Access Clarity | 36.8 |

Regulatory layer — **Horizontal (data, software, accessibility, platform)**: 9.1 (matched via fallback).

## Agent readiness — 0.0 (human-only)

| Dimension | Value |
|---|---|
| Spec Presence | no |
| Agentic Access | no |
| Reversibility Documented | no |
| MCP Server | no |
| Auth Clarity | no |
| Idempotency | no |
| Error Semantics | no |
| OpenAPI Examples | no |
| Rate Limit Signal | no |
| Event Surface Described | no |
| Agent Skills | no |
| Well Known Catalog | no |
| Consent Identity | no |
| Agent Card | no |
| Dry Run Mode | no |
| Delegated Identity | no |
| Protected Resource Metadata | no |
| Dynamic Client Registration | no |
| Agentic Commerce | no |
| Pagination Ratio | na |
| Operation Distinctiveness | na |
| MCP Tool Quality | na |

## Access

Freemium — onboarding: unknown, pricing: freemium, trial: no (confidence: low).

## Security (1)

- **Agentcouch Domain Security** — TLSv1.3 · HSTS

## Plans (1)

- **Agentcouch Plans Pricing**

## Tags

Company, Messaging, Artificial Intelligence, Collaboration, MCP

---

Profiled by [API Evangelist](https://apievangelist.com) and published on [APIs.io](https://apis.io/providers/agentcouch/). Scores are computed from the provider's own public artifacts under a published rubric.