ai.roxels/roxels-mcp
Roxels
Is the Roxels MCP server down? No. Installed with mcp<2, it started and listed its tools on 2026-11-02.
Let AI agents create configurable voice agents via meeting rooms and return structured data.
needs mcp<2 probed 2026-11-14 · unchanged since 2026-11-02
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 2026-11-02.
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' roxels-mcp@0.5.1 (stdio, probed in a container with the network off)
- Host
- pypi.org
- Reports itself as
- roxels 1.30.0
- Capabilities
- experimental, prompts, resources, tools
- Repository
- https://github.com/trebu-org/interviewer
- Registry
- active, updated 2026-04-08 · registry entry
- Changes
- 2 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 |
|---|---|---|
| update_template | 278 | 10 % |
| configure_output | 254 | 9 % |
| create_template | 237 | 9 % |
| list_interviews | 210 | 8 % |
| get_embed_code | 199 | 7 % |
Compare this server with others.
More servers
Other registry entries on pypi.org, the ones next to this name; all of them.
- MIRASTACK Redfish MCP Server ai.mirastacklabs/mirastack-redfish-mcp · needs network
- Nauro ai.nauro/nauro · alive
- NexusToken ai.nexustoken/nexustoken-sdk · crashed on start
- xbrlkit ai.robosystems/xbrlkit · needs args
- SkillTotal ai.skilltotal/skilltotal · alive
- SmartMemory ai.smartmemory/smartmemory-mcp · alive
- Solwyn ai.solwyn/solwyn · needs args
- ai.sovantica/engrava · needs env
Servers that mention configurable or structured.
- AkkruData ai.akkrudata/akkrudata · needs auth
- Lenny Rachitsky Podcast Transcripts MCP Server ai.com.mcp/lenny-rachitsky-podcast · alive
- ai.extend/extend · needs auth
- ai.getvda/claude-schema-output-agent · newer protocol
- ai.getvda/structured-output-agent · newer protocol
- ai.getvda/structured-output-agent-c2ddcc · newer protocol
- ai.getvda/structured-output-agent-openai · newer protocol
- ai.getvda/structured-output-mcp-agent-instructor · newer protocol
History
We add a row when the result changes. A server with no change keeps its last row.
| Probed | Result | Init | Tools | Claude | o200k |
|---|---|---|---|---|---|
| 2026-11-02 08:17 | needs mcp<2 | 1.4 s | 19 | 4.7k | 2.7k |
| 2026-10-19 06:49 | 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'