docs(blog): introduce mcp-graphql #6825
Conversation
|
Important Review skippedAuto reviews are disabled on this repository. Please check the settings in the CodeRabbit UI or the You can disable this status message by setting the ✨ Finishing touches🧪 Generate unit tests
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
|
|
||
| TL;DR | ||
|
|
||
| - The GraphQL MCP server allows your AI models to interact with your GraphQL server |
There was a problem hiding this comment.
Maybe worth mentioning in as many places as possible, that this works with ANY GraphQL server and you don't and shouldn't need any vendor specific solution in general
| With traditional MCP servers, this would require separate tools for users, posts, filtering, and sorting - if you even anticipated this exact combination. | ||
|
|
||
| ## The future | ||
| - Tools per operation |
There was a problem hiding this comment.
Turn that into text
also maybe link to PRs or issues on the repo
and expand more on the idea of how to connect to Hive Console
|
|
||
| You can track progress for it on [this PR](https://github.com/blurrah/mcp-graphql/pull/3) | ||
|
|
||
| Will also support persisted documents in the future allowing you to work with production API's that lock down calls |
There was a problem hiding this comment.
| Will also support persisted documents in the future allowing you to work with production API's that lock down calls | |
| This feature will also support [persisted documents](https://the-guild.dev/graphql/hive/docs/schema-registry/app-deployments) in the future, allowing you to work with production API's that lock down calls. |
Minor grammar changes and link to our trusted docs implementation for clarification on what persisted docs are and how to use them.
| You can track progress for it on [this PR](https://github.com/blurrah/mcp-graphql/pull/3) | ||
|
|
||
| Will also support persisted documents in the future allowing you to work with production API's that lock down calls | ||
|
|
There was a problem hiding this comment.
a small conclusion or call to action is appropriate.
E.g. If you're interested in contributing to the mcp-graphql project or want to learn more, then ...
| --- | ||
| title: 'Introducing: GraphQL MCP server' | ||
| authors: blurrah | ||
| tags: [graphql, mcp] |
There was a problem hiding this comment.
| tags: [graphql, mcp] | |
| tags: [graphql, ai] |
If we want to limit the number of tags, ai would be better to use than mcp since we can attribute more articles to that.
| title: 'Introducing: GraphQL MCP server' | ||
| authors: blurrah | ||
| tags: [graphql, mcp] | ||
| date: 2025-05-26 |
There was a problem hiding this comment.
| date: 2025-05-26 | |
| date: 2025-09-26 |
adjust date since we're slow at approving
| - You can access it at [github.com/blurrah/mcp-graphql](https://github.com/blurrah/mcp-graphql) | ||
|
|
||
| ------ | ||
| Most MCP servers force you to create narrow, specific tools for each API endpoint. Want to query user data? One tool. Need to fetch posts? Another tool. Want to combine users and their posts? You're out of luck unless you anticipated that exact use case. |
There was a problem hiding this comment.
| Most MCP servers force you to create narrow, specific tools for each API endpoint. Want to query user data? One tool. Need to fetch posts? Another tool. Want to combine users and their posts? You're out of luck unless you anticipated that exact use case. | |
| Most Model Context Protocol (MCP) servers force you to create narrow, specific tools for each API endpoint. Want to query user data? One tool. Need to fetch posts? Another tool. Want to combine users and their posts? You're out of luck unless you anticipated that exact use case. |
it's nice to say what it is before using acronym.
|
@blurrah sorry for the delay in reviewing this. We're still very interested in getting this posted. |
Background
This adds a blog post to introduce the
mcp-graphqlserver.Description
This is a blog post introducing the
mcp-graphqlserver and what it does, why MCP and GraphQL work very well and it's future goals. This is a really early rough draft.Checklist
Not needed for a blog post.