Skip to main content

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)

Metadata

Release files for mcp-psilo-mock 0.1.19

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for mcp-psilo-mock 0.1.19
File Size Uploaded Provenance
mcp_psilo_mock-0.1.19.tar.gz 6.2 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for mcp-psilo-mock 0.1.19
File Interpreter ABI Platform
mcp_psilo_mock-0.1.19-py3-none-any.whl Python 3 none any Details

Total release size: 12.5 kB

Release files / mcp_psilo_mock-0.1.19.tar.gz

Download URL mcp_psilo_mock-0.1.19.tar.gz
Size 6.2 kB
Tags Source
SHA-256 checksum
How to use checksums
8f114f13e15e1559a24a24d87dabe0f5cc94cd27a10d672de36c43c81fe126e2
BLAKE2b-256 checksum
How to use checksums
2cec7a44fc840c47b5e589b0acb13744aca3c6ddafcf9f5cf76a42bc5d04ac18
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.11.9

Release files / mcp_psilo_mock-0.1.19-py3-none-any.whl

Download URL mcp_psilo_mock-0.1.19-py3-none-any.whl
Size 6.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
f8c0ec64aee806b2e15ba8fb59bdaf7905c5b03cc6a0f0629718e2bc741b8ea7
BLAKE2b-256 checksum
How to use checksums
34b89e4bec8e2b243168d683abb9af9b66485854fcf10dce9eaebb20662b2636
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.1.0 CPython/3.11.9

Security for mcp-psilo-mock 0.1.19

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page