spring-projects / spring-projects/spring-ai
How can I monitor the process of MCP service calls
Nobody has claimed this yet.
- Dominant language
- Java
- Stars
- 9.5k
- Forks
- 2.9k
- Avg merge
- 1d 7h
- Merged PRs (30d)
- 6
Description
I can register tools provided by MCP services through tools or toolcallbacks. However, is there any way for LLM to enhance or intercept tool calls before and after MCP service tool calls, similar to the AOP aspect? For example, I want to know how to optimize user input or output of large models before tool calls, and then determine whether to continue execution after tool calls ..
Contributor guide
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
Start by reviewing the tools and toolcallbacks used to register MCP service tools, then trace where MCP service tool calls enter and return. The issue asks for before-and-after interception and conditional continuation, but names no files or tests and does not define a concrete completion criterion.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- java, spring
- Domain
- ai
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100