DOC-815 | MCP Server #820
Open
DOC-815 | MCP Server #820
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
|
Deploy Preview Available Via |
diegomendez40
requested review from
bluepal-keerthi-datla,
diegomendez40 and
maxkernbach
Simran-B
reviewed
Nov 4, 2025
| 2. Start ArangoDB (if you don't have an instance): | ||
|
|
||
| ```bash | ||
| docker run -d --name arangodb -p 8529:8529 -e ARANGO_ROOT_PASSWORD=test arangodb/arangodb:latest |
There was a problem hiding this comment.
Should use image arangodb or arangodb/enterprise. We no longer publish arangodb/arangodb (CE) since 3.12.5
nerpaula
commented
Nov 4, 2025
| @@ -0,0 +1,322 @@ | |||
| --- | |||
| title: ArangoDB Model Context Protocol (MCP) Server | |||
There was a problem hiding this comment.
@diegomendez40 should we mark it as experimental?
Simran-B
reviewed
Nov 4, 2025
| description: >- | ||
| A Model Context Protocol server for generating and executing AQL queries using AI assistants like Claude and Cursor IDE | ||
| --- | ||
| The ArangoDB MCP Server is a focused [Model Context Protocol](https://modelcontextprotocol.io/) (MCP) implementation that enables AI assistants to generate and execute AQL queries based on natural language questions. It includes lightweight schema discovery and manuals to ground queries in actual database structure. |
There was a problem hiding this comment.
Suggested change
| The ArangoDB MCP Server is a focused [Model Context Protocol](https://modelcontextprotocol.io/) (MCP) implementation that enables AI assistants to generate and execute AQL queries based on natural language questions. It includes lightweight schema discovery and manuals to ground queries in actual database structure. | |
| The ArangoDB MCP Server is a focused [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) | |
| implementation that enables AI assistants to generate and execute AQL queries | |
| based on natural language questions. It includes lightweight schema discovery | |
| and manuals to ground queries in actual database structure. |
maxkernbach
reviewed
Nov 5, 2025
There was a problem hiding this comment.
@nerpaula For now we are planning to keep the MCP repository private, which means that users/customers do not need any local docker or poetry instructions.
Instead, the MCP docker images are uploaded to docker hub . The linked docker hub page also includes instructions on how to use the MCP.
- How are we planning to proceed with the documentation? We should decide whether we want to maintain the detailed docs on docker hub or in our official documentation - What do you prefer?
- Also, have all the listed examples in the "Practical Examples" section been validated to work with the first MCP version?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Description
TO DO: Add official Docker Hub image once it has been published.