io.github.Applied-Artificial-Intelligence-Eurecat/epanet-mcp-server
EPANET MCP Server
Is the EPANET MCP server down? No. Installed with mcp<2, it started and listed its tools on 2026-11-14.
MCP server for EPANET water-distribution network simulation and scenario analysis.
needs mcp<2 probed 2026-11-15 · unchanged since 2026-11-14
A plain install of the package stops at the import below. These tool definitions are from a second install with mcp<2, started in a container with the network off, on 2026-11-14.
MCP error -32000: Connection closed ModuleNotFoundError: No module named 'mcp.server.fastmcp'. This is mcp 2.x, where FastMCP was renamed to MCPServer (from mcp
- Run it
- uvx --with 'mcp<2' epanet-mcp-server@0.2.0 (stdio, probed in a container with the network off)
- Host
- pypi.org
- Reports itself as
- EPANET MCP Server 1.30.0
- Capabilities
- experimental, prompts, resources, tools
- Repository
- https://github.com/Applied-Artificial-Intelligence-Eurecat/epanet-mcp-server
- Registry
- active, updated 2026-11-13 · registry entry
- Changes
- 3 recorded, reachable in 0 of them. A row is added when the result, the tool count or the cost changes.
Most expensive tools
Estimates with the o200k_base tokenizer.
| Tool | o200k estimate | Share of this server |
|---|---|---|
| create_contamination_event | 410 | 6 % |
| create_leakage_event | 398 | 6 % |
| create_pump_control_scenario | 290 | 4 % |
| create_multi_failure_scenario | 260 | 4 % |
| set_tank_parameters | 256 | 4 % |
Compare this server with others.
More servers
Other registry entries on pypi.org, the ones next to this name; all of them.
- io.github.Antmanbuilds/ari-mcp-py · crashed on start
- TrainTools io.github.AparajeetS/traintools · needs args
- io.github.Apheironn/pasr · needs args
- RSI Boot io.github.Apollo-lwx/rsi-boot · alive
- Arc Free Skills io.github.ArcHelps/arc-free-skills · needs args
- io.github.Archerkattri/mathlas · alive
- io.github.ArchiPlan-io/production-scheduling-mcp · alive
- io.github.Areso/safe-ssh-mcp · crashed on start
Servers that mention distribution or simulation.
- Supreme Mind ai.suprememind/expert-witness-simulation · needs auth
- Pokemon TCG Pocket Catalog app.hologallery.pocket/pokemon-tcg-pocket-catalog · alive
- ONCE app.once/mcp · needs auth
- 3DOptix com.3doptix/optical-design · needs auth
- Agent Distribution com.agentdistributionservices/agent-distribution · alive
- Alchemy MCP Server com.alchemy/mcp · needs auth
- com.applivery.docs/mcp · alive
- DAG Studio MCP com.blackswancausallabs/dagstudio-mcp · needs auth
History
We add a row when the result changes. A server with no change keeps its last row.
| Probed | Result | Init | Tools | Claude | o200k |
|---|---|---|---|---|---|
| 2026-11-14 08:03 | needs mcp<2 | 3.2 s | 45 | 12k | 6.7k |
| 2026-11-06 08:34 | needs mcp<2 | 3.8 s | 44 | 11k | 6.4k |
| 2026-10-16 06:24 | crashed on start |
Badge for the README
The result of the latest probe, the tool count and the token cost. The feed has an entry for every probe that changed them.
A mail when this server changes
Stops answering, comes back, tool set or cost changes. One confirmation mail first, a stop link in every mail.
For the publisher
- The package imports FastMCP from mcp.server.fastmcp. mcp 2.0, the Python SDK of 28 July 2026, renamed FastMCP to MCPServer, and the package asks for mcp with no upper bound, so a plain install (uvx, pip) gets mcp 2.x and the server stops at the import. Installed with mcp<2, it starts and lists its tools. The fix for the publisher: pin mcp<2 in the dependencies, for example mcp>=1.2,<2, and publish a new version, or move to MCPServer as the SDK's migration guide says. Until then, run it with uvx --with 'mcp<2'.
The cause and the fix, with the code before and after: ModuleNotFoundError: No module named 'mcp.server.fastmcp'