# Large Tool Contexts from Apollo MCP Server?

**URL:** <https://community.apollographql.com/t/large-tool-contexts-from-apollo-mcp-server/9354>\
**Category:** MCP Server\
**Created:** [August 6, 2025, 4:40pm UTC](https://community.apollographql.com/t/large-tool-contexts-from-apollo-mcp-server/9354 "2025-08-06T16:40:09Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![thdesc](https://sea1.discourse-cdn.com/flex019/user_avatar/community.apollographql.com/thdesc/32/6305_2.png) [@thdesc](https://community.apollographql.com/u/thdesc)\
**Post date:** [August 6, 2025, 4:40pm UTC](https://community.apollographql.com/t/large-tool-contexts-from-apollo-mcp-server/9354/1 "2025-08-06T16:40:09Z")

</div>

Hi everyone! Thanks for the great work!

I’m running an MCP server using the Docker image `ghcr.io/apollographql/apollo-mcp-server:latest`. The container spins up successfully. I have an `operations` folder with 8 operations, and a fairly large GraphQL schema (around 9,000 lines).

When I run the server, the logs show the estimated token size for each tool created. The largest one in my case is 13,665 tokens, with a total across all tools of 31,657 tokens. I’ve also enabled introspection queries.

I’m connecting Claude Desktop (using Claude Sonnet 4.0 with a 200k context window) to this MCP server, but I’m unable to make any queries because the context appears to be too large. Has anyone else run into a similar issue?

I was under the impression that only the tool name and description were exposed to the MCP client/host, so I’m surprised the token count is this high. Any ideas or suggestions would be greatly appreciated—thanks!