AtlasRepo MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ATLASREPO_API_KEY | No | API key for authentication if the API requires it. | |
| ATLASREPO_API_BASE_URL | No | Override the default API base URL. For example, set to http://localhost:8787 for development. | https://atlasrepo.com |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| atlasrepo_recommendA | Find evidence-backed repositories and workflows for a concrete engineering or content-production problem. |
| atlasrepo_search_toolsB | Search normalized open-source tools by text, kind, and quality threshold. |
| atlasrepo_get_repositoryA | Load the AtlasRepo decision record and linked evidence for one GitHub repository. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
The tools are mostly distinct: atlasrepo_recommend is problem-driven, atlasrepo_search_tools is structured query-based, and atlasrepo_get_repository is a targeted detail fetch. However, recommend and search_tools could both return repositories/tools, so an agent might occasionally be unsure which path to use for discovery.
All tools share the atlasrepo_ prefix and use a verb-first style. atlasrepo_search_tools and atlasrepo_get_repository follow a clear verb_noun pattern, but atlasrepo_recommend lacks an object, creating a minor inconsistency.
Three tools is well-scoped for this domain: one for problem-level recommendation, one for structured search, and one for inspecting a specific repository record. Each tool covers a distinct part of the workflow without redundancy.
The read-only decision-record workflow is well covered: discover by problem, search by criteria, and load detailed evidence for a repository. Minor gaps include no explicit list-all/browse capability or a dedicated workflow-detail fetch, but these are workable through the existing tools.