run

THE RISK

Low Risk

Why run needs a policy

This tool only fetches/retrieves information about a specific analysis run using an identifier. There are no side effects, modifications, or destructive actions involved.

From the tool's definition 'Get a specific analysis run by its runUid or commitOid' - purely retrieves data about an analysis run

Documented attack patterns abuse exactly the kind of access run gives an agent:

POLICY

How to control run

PolicyLayer is an MCP gateway — it sits between your AI agents and DeepSource MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for run:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "run": {}
  }
}

run is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register DeepSource MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More DeepSource MCP Server tools

Write update_metric_setting Update the settings for a quality metric Write update_metric_threshold Update the threshold for a specific quality metric Read recent_run_issues Get issues from the most recent analysis run on a specific branch Read compliance_report Get security compliance reports from a DeepSource project Read dependency_vulnerabilities Get dependency vulnerabilities from a DeepSource project Other example_tool An example tool demonstrating the enhanced plugin format Read project_issues Get issues from a DeepSource project with filtering capabilities Read projects List all available DeepSource projects. Returns a list of project objects with

All 11 DeepSource MCP Server tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about run

What does the run tool do? +

Get a specific analysis run by its runUid or commitOid. It is categorised as a Read tool in the DeepSource MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on run? +

Register the DeepSource MCP Server MCP server in PolicyLayer and add a rule for run: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches DeepSource MCP Server. Nothing to install.

What risk level is run? +

run is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit run? +

Yes. Add a rate_limit block to the run rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block run completely? +

Set action: deny in the PolicyLayer policy for run. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides run? +

run is provided by the DeepSource MCP Server MCP server (sapientpants/deepsource-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every DeepSource MCP Server tool call.

Start from DeepSource MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →