Developer · Local MCP server
AgentSUMO
MCP server for LLM-driven SUMO traffic simulation, scenario design, and result analysis.
What the MCP Registry states
The entry as published to the official MCP Registry (read 2026-10-04), latest version.
- Registry name
io.github.mw-jeong/agentsumo-mcp- Version
- 0.1.2
- Status
- Active
- Category
- developer
- Transport
- stdio (local process)
- Package
- PyPI
- Published
- 2026-06-05
- Updated
- 2026-06-05
- Publisher
- mw-jeong (GitHub)
- Namespace
- Namespace verified by the MCP Registry via GitHub (github.com/mw-jeong) · how
- Repository
- github.com/mw-jeong/AgentSUMO
- Source
- Registry API entry
Packages
| Registry | Package | Version | Transport |
|---|---|---|---|
| PyPIruntime: uvx | agentsumo-mcp | 0.1.2 | stdio |
How to connect AgentSUMO
AgentSUMO runs locally from a Python package published to PyPI: agentsumo-mcp version 0.1.2. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Python; clients usually start it with uvx (from uv) or after pip install - the usual command is uvx agentsumo-mcp. It reads these environment variables: SUMO_HOME (required) and AGENTSUMO_MCP_OUTPUT_BASE; set them in the client's configuration for this server.
In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):
{
"mcpServers": {
"agentsumo-mcp": {
"command": "uvx",
"args": [
"agentsumo-mcp"
],
"env": {
"SUMO_HOME": "<value>",
"AGENTSUMO_MCP_OUTPUT_BASE": "<value>"
}
}
}
}Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect
More developer servers
| Server | Runs |
|---|---|
| Agentskillupdategate MCPPaid remote MCP for Claude Code skill update gate MCP, structured receipts, audit logs, and reviewer. | Remote · HTTPLive check: ✗ no handshake |
| AgentsnapSnapshot tests for AI tool-call traces: diff, validate, and catch silent regressions. | Local · stdio |
| AgentSpaceGive your agent a persistent workspace: files, a code sandbox and a public URL to publish to. | Remote · HTTPLive check: sign-in required |
| AgentSQLGuard AI agents' PostgreSQL/MySQL access via MCP: SQL audit, auth, masking, write approval. | Remote · HTTPLive check: sign-in required |
| agentsyncMulti-agent coordination MCP: claim work, survey peers, resolve conflicts via a git branch as CAS. | Local · stdio |
| AgenttunePersonality tuning files for AI agents: 43 MIT-licensed tunings + 5 inline personality tests. | Remote · HTTPLive check: ✓ handshake |
| Agentverse MemoryGraph-native persistent memory for AI agents - 33 MCP tools, zero-LLM writes. | Remote · HTTPLive check: sign-in required |
| AgentvetValidate tool-call args before execution. Returns LLM-friendly retry hints. | Local · stdio |