feat(MCP): Make Wiki-RAG to behave as a MCP server #7
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This brings Model Context Protocol (MCP) server support to Wiki-RAG
providing all the features already available in the OpenAI server
and more:
- Prompts:
- get_system_prompt: Get the system prompt, optionally parsing arguments.
- get_user_prompt: Get the user prompt, optionally parsing arguments.
- Tools:
- retrieve: Get the raw results from the (vector) database.
- optimise: Post-process the results providing the optimised context
and sources.
- generate: Run the whole stack, returning the answer from the LLM.
- Resources:
- get_10_pages: Return the first 10 parsed pages from the target wikis.
- get_100_pages: Return the first 100 parsed pages from the target wikis.
- get_pages/start/number: Return the specified number of pages from a given start.
Important: The whole MCP server is UNPROTECTED, so take it into
account depending of the deployments planned.
This is only a demo implementation to play with MCP and see how
easy is to transform any other existing API to be MCP-compatible.
Fixes moodlehq#4
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This brings Model Context Protocol (MCP) server support to Wiki-RAG providing all the features already available in the OpenAI server and more:
Important: The whole MCP server is UNPROTECTED, so take it into
account depending of the deployments planned.
This is only a demo implementation to play with MCP and see how easy is to transform any other existing API to be MCP-compatible.
Fixes #4