Skip to main content

Mock MCP server tools for psilo model context protocol

Project description

MCP for PSILO

There are 3 main folders:

  • mcp_psilo_in_progress/
    • Code being developed (in progress)
      • client_sse.py, client_stdio.py, server_sse.py all work
      • client_http.py, server_http.py does not work
  • mcp_psilo_mock/
    • This code is published in PyPI: https://pypi.org/project/mcp-psilo-mock/
      • server_stdio.py contains the key get_psilo_data function
      • server_stdio2.py contains is an extra stdio_server used to test connecting to multiple MCP servers with Claude desktop
  • test_code/
    • test_right_package.py Contains scripts to run the servers and clients in the two above folders
      • test_right_package.py is used to determine where mcp_psilo_mock is coming from (from this repo or from the published package) [this was cerated to assist when deploying the package]
    • test_run_sse_client.py is not importing the sse_client package from mcp; an alternative must be found
    • test_run_sse_server.py, test_run_stdio_client.py, test_run_stdio_server.py, and test_run_stdio_client.py all work

Archived notes

server_stdio.py and client_stdio.py both work with standard input/output. However, the client runs the server as a subprocess.

We need the server to run independently (and connect via something like http). server_http.py and client_http.py are attempts to have it work, but connection through http doesn't work with the current mcp library.

The issues with running http are found below:

  1. FastMCP has no .app or .asgi_app() method
    • So you can’t do: uvicorn.run(mcp.app, ...)
    • This makes it incompatible with uvicorn in current form
  2. FastMCP.run() only supports stdio, not network transport
  3. fastapi_mcp not viable or missing
    • Either unavailable, misinstalled, or not meant for your current MCP version
  4. HTTP-based tool exposure not built-in in your installed MCP version
    • You’d have to write a manual FastAPI wrapper (no real MCP involved)

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mcp_psilo_mock-0.1.18.tar.gz (6.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mcp_psilo_mock-0.1.18-py3-none-any.whl (6.4 kB view details)

Uploaded Python 3

File details

Details for the file mcp_psilo_mock-0.1.18.tar.gz.

File metadata

  • Download URL: mcp_psilo_mock-0.1.18.tar.gz
  • Upload date:
  • Size: 6.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.11.9

File hashes

Hashes for mcp_psilo_mock-0.1.18.tar.gz
Algorithm Hash digest
SHA256 469428255e3420a58d4e0fb1d0a605db567a661cd94ad13a201ccc2f2076ee3e
MD5 7ab049400088edb5ebbb88afbd318208
BLAKE2b-256 cd9452f8fb59871f1d69ed63e5be7b96da3caa78d5d0f996da92a8d98e21687f

See more details on using hashes here.

File details

Details for the file mcp_psilo_mock-0.1.18-py3-none-any.whl.

File metadata

File hashes

Hashes for mcp_psilo_mock-0.1.18-py3-none-any.whl
Algorithm Hash digest
SHA256 3f2dfd48e411ad431e0270bd1a0461d6c71541d0257d01389e4c19795afd3cb3
MD5 1c0758933b9e0cbcf98b4ed180820c14
BLAKE2b-256 b7f9f55add7abb7524f44ffda28eef1e2b91afc43f943d4b76f9ee48e619ed2a

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page