io.github.Octid-io/osmp
osmp
Is the io.github.Octid-io/osmp MCP server down? No. Installed with mcp<2, it started and listed its tools on 2026-11-02.
Agentic AI instruction encoding. 86.8% vs JSON. Inference-free decode. Any channel.
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' osmp-mcp@1.3.3 (stdio, probed in a container with the network off)
- Host
- pypi.org
- Reports itself as
- osmp 1.30.0
- Capabilities
- experimental, prompts, resources, tools
- Repository
- https://github.com/octid-io/cloudless-sky
- Registry
- active, updated 2026-05-06 · 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 |
|---|---|---|
| osmp_eml_evaluate | 416 | 12 % |
| osmp_discover | 282 | 8 % |
| osmp_resolve | 255 | 8 % |
| osmp_encode | 239 | 7 % |
| osmp_eml_corpus_lookup | 223 | 7 % |
Compare this server with others.
More servers
Other registry entries on pypi.org, the ones next to this name; all of them.
- DICOM/HL7/FHIR Interoperability MCP Server io.github.NyxToolsDev/dicom-hl7-mcp-server · crashed on start
- io.github.NyxToolsDev/quickbooks-mcp-server · crashed on start
- adhistory: Google Ads, reviews, jobs, PDFs io.github.OBrandon/adhistory-mcp · alive
- nanomem io.github.OmBansod2/nanomem · crashed on start
- Section Anything io.github.Omniwot/section-anything · alive
- FileSystem MCP Server io.github.Oncorporation/filesystem-server · alive
- io.github.ONSBR/tiago-dados-abertos · needs env
- io.github.OnticX/open-mcp-registry · crashed on start
Servers that mention instruction or inference.
- inference.sh ac.inference.sh/mcp · needs auth
- Mekler AI ai.mekler/agent-discovery · alive
- Zhijiangyun Cloud (智匠云) cloud.artibot/zhijiangyun · needs auth
- InternationalCall.co dialing co.internationalcall/dialing · alive
- com.ai-rook.agents/trading-mcp · alive
- com.cheapestinference/mcp · alive
- ComputeSage StackBench com.computesage/stackbench · alive
- JSON to Types com.gumballtools/json-to-types · alive
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 08:24 | needs mcp<2 | 1.7 s | 19 | 6.2k | 3.3k |
| 2026-10-19 06:53 | 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'