Letta Railway
This Railway-deployable MCP server implementation by SNYCFIRE-CORE bridges AI clients with Letta.ai agents through HTTP transport, enabling stateful conversations without requiring clients to manage conversation history. Built with FastMCP and Python, it provides comprehensive agent lifecycle management (creation, configuration, deletion), memory block operations for persistent context storage, tool attachment/detachment capabilities, and conversation export functionality. The implementation includes robust error handling, retry logic, streaming support, and Railway-specific deployment configurations, making it particularly useful for teams wanting to integrate Letta's stateful AI agents into existing workflows through any MCP-compatible client like Claude Desktop, GitHub Copilot, or Cursor while maintaining persistent agent memory across sessions.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-19.
Scan details: Circle-IR · 2026-09-19 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- version-control
- Source
- PulseMCP
- Author type
- human
- Last scanned
- 2026-09-19
- Updated
- 2026-09-19
Use via MCP
Resolve Letta Railway 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.