Agent Mail
A coordinated multi-agent messaging and coordination MCP server that enables AI agents to communicate through structured messages, claim exclusive access to file paths, and maintain persistent project archives with Git-based version control. Built with FastMCP, SQLModel, and PostgreSQL, it features full-text search capabilities, acknowledgment tracking, attachment processing with automatic image conversion to WebP, and pre-commit guards that prevent conflicting file modifications across agents. The system organizes agents into projects with human-readable names, stores all communications in both database and filesystem archives, and includes comprehensive CLI tooling for project management, claims inspection, and acknowledgment monitoring, making it useful for coordinating multiple AI agents working on shared codebases or collaborative tasks where conflict prevention and communication history are essential.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Repository
- github.com/dicklesworthstone/mcp_agent_mail
- Author type
- human
- Updated
- 2026-05-27
Use via MCP
Resolve Agent Mail from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.