modelcontextprotocol / modelcontextprotocol/servers
Sequential Thinking: Add option to use API requests to help with usage limits / maximum response length
Nobody has claimed this yet.
- Dominant language
- TypeScript
- Stars
- 90.5k
- Forks
- 11.7k
- Avg merge
- 2d 2h
- Merged PRs (30d)
- 5
Description
Is your feature request related to a problem? Please describe.
While quite useful, this feature can frequently hit the length limit, and isn't ideal when many of us already struggle with usage limitations.
Describe the solution you'd like
There a number of servers that allow making API calls.
Ideally this could be implemented directly, otherwise the ability to specify another MCP tool to use for Sequential-Thinking would make it possible to offload the thinking to Claude via the Anthropic or Open Router APIs.
(the latter would also support any other model.)
Additional context
The vast majority of MCP users either already have an Anthropic API key, or can easily figure out how to get one.
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 locating the Sequential Thinking server and reviewing its MCP tool interface. Compare the requested direct API support with delegation to another MCP tool, using the Anthropic and Open Router APIs named in the issue as context. Done requires an agreed implementation path and defined behavior for usage limits and maximum response length.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- typescript
- Domain
- ai, api
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100