Is interaction with MCP tool possible?
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 10.5k
- Forks
- 1.2k
- Avg merge
- 4m
- Merged PRs (30d)
- 1
Description
Feature Request:
Currently, the Ollama Python client does not seem to support consuming remote tools from Model Context Protocol (MCP) servers directly. For workflows requiring LLM tool calling functionality via the MCP protocol (e.g., running tool servers remotely, using MCP stdio or http), users have to rely on external adapters or other community projects rather than native support in this client.
Expected Behavior:
It would be very helpful if the ollama-python library could natively connect to remote MCP servers, discover and invoke tools provided via the MCP protocol, and incorporate those results into LLM responses, similar to how some community adapters do.
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
No files or tests are named in the issue. Start by reviewing the ollama-python client API and the MCP protocol requirements, including remote, stdio, and HTTP server usage. Done means the library can connect to MCP servers, discover and invoke their tools, and include tool results in LLM responses with suitable coverage.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- api, backend-api-design
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 25/100