How to Use the DeepSource MCP in Pydantic AI

Q: How do I connect the DeepSource MCP Server to Pydantic AI?

Install pydantic-ai-slimmcp. Initialize an MCPToolset with your HTTP endpoint and pass it to your Agent's toolsets array. The server must be running externally.

Q: Will Pydantic AI catch missing DeepSource metrics?

Yes. When your agent calls getrepositorymetrics, the framework validates the response against your defined models. If a metric is missing or malformed, the agent throws a validation error immediately.

Q: How does Pydantic AI rotate DeepSource credentials?

The agent executes regeneratedsn using the target repository ID. This instantly invalidates the old Data Source Name and returns a fresh one for your CI/CD pipelines.

Q: Can I filter DeepSource issues using Pydantic AI?

Your agent calls listissues and passes analyzer shortcodes like "PYTHON" or "JS-A1". It limits the results to a specific count to keep the context window clean.

Type-safe DeepSource MCP Server integration for Pydantic AI. Validate code metrics, CVE IDs, and repository data at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DeepSource MCP to Pydantic AI

Create your Vinkius account to connect DeepSource to Pydantic AI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup DeepSource with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe security scans via MCP Server

`list_vulnerabilities` pulls dependency flaws and forces them through Pydantic's validation models. Your agent gets guaranteed types for CVSS scores, severity strings, and CVE IDs. `get_vulnerability` fetches the deep-dive details for a specific flaw using its occurrence ID. Supply chain tracking relies on `list_sca_targets`. This tool returns the ecosystem, package manager, and manifest file path. If the DeepSource API returns an unexpected data type, your Pydantic AI agent fails loudly instead of hallucinating a fix for the wrong package.

Control analysis state and configuration

`activate_repository` turns on code quality tracking for a specific project. `deactivate_repository` stops the analysis and halts billing. Both tools require the repository ID, which your agent fetches by running `get_repository` through the MCP Server first. Branch management happens through `update_default_branch`. You pass the repository ID and the new branch string to shift the analysis target. `regenerate_dsn` rotates the authentication keys used for pipeline runs, invalidating the old DSN immediately.

Extract typed code quality metrics

`get_repository_metrics` returns specific data points like line coverage or maintainability index based on shortcodes. `get_test_coverage` pulls the exact coverage percentage and configured thresholds. Pydantic AI ensures these numbers are parsed as floats or integers, never strings. `list_issues` gathers code smells and anti-patterns across the codebase. `list_analysis_runs` shows which language analyzer fired and its success state. `get_report_card` provides the high-level grade, giving your agent a strict, validated view of project health.

Setup guide

Set up DeepSource MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "deepsource-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to DeepSource tools.",
)

result = await agent.run("List recent DeepSource transactions")
print(result.output)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by DeepSource. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect DeepSource now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about DeepSource MCP in Pydantic AI

Install `pydantic-ai-slim[mcp]`. Initialize an `MCPToolset` with your HTTP endpoint and pass it to your Agent's `toolsets` array. The server must be running externally.

Yes. When your agent calls `get_repository_metrics`, the framework validates the response against your defined models. If a metric is missing or malformed, the agent throws a validation error immediately.

The agent executes `regenerate_dsn` using the target repository ID. This instantly invalidates the old Data Source Name and returns a fresh one for your CI/CD pipelines.

Your agent calls `list_issues` and passes analyzer shortcodes like "PYTHON" or "JS-A1". It limits the results to a specific count to keep the context window clean.

Tokens remain outside the LLM context. The Pydantic AI framework sends the execution request to the Vinkius managed endpoint, which handles the auth layer. Only the resulting metric values and vulnerability strings return to your local environment.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript