DeepSource MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DEEPSOURCE_API_KEY | Yes | Your DeepSource API key for authentication with the DeepSource API |
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 |
|---|---|
| projectsA | List all available DeepSource projects. Returns a list of project objects with "key" and "name" properties. |
| quality_metricsB | Get quality metrics from a DeepSource project with optional filtering |
| update_metric_thresholdC | Update the threshold for a specific quality metric |
| update_metric_settingC | Update the settings for a quality metric |
| compliance_reportA | Get security compliance reports from a DeepSource project |
| project_issuesB | Get issues from a DeepSource project with filtering capabilities |
| runsA | List analysis runs for a DeepSource project with filtering |
| runB | Get a specific analysis run by its runUid or commitOid |
| recent_run_issuesB | Get issues from the most recent analysis run on a specific branch |
| dependency_vulnerabilitiesB | Get dependency vulnerabilities from a DeepSource project |
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 10 tools
Most tools have clearly distinct purposes (projects vs runs vs issues vs metrics vs security). However, project_issues and recent_run_issues both deal with issues and could cause initial confusion, though descriptions clarify the difference.
Tool names follow a predictable pattern: query tools are named after the resource (noun or noun phrase, e.g., projects, runs, quality_metrics) and mutation tools use verb_resource (e.g., update_metric_setting). This is consistent and readable.
10 tools is well-scoped for a code analysis server, covering core areas (projects, runs, issues, metrics, compliance, dependencies) without being overwhelming or too sparse.
The tool set covers most essential operations (list, get, update for key resources) but lacks branch listing (needed for recent_run_issues) and triggering analysis runs, which are notable gaps for a comprehensive interface.