auto_remediate

SERVERMcp Server SOURCE@graneth/mcp-server

Medium RISK CLASS

Category Write

Parameters 1110 required

Recommended Rate-limitedsee the rule below

Registry record Grade D, identity unverified Pull the record →

This record as markdown: /tools/com-graneth-mcp-server/auto-remediate.md

WHAT IT DOES

What auto_remediate does on Mcp Server

AI agents use auto_remediate to create or update resources in Mcp Server, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Server environment.

Parameter	Type	Required	Description
`ref`	string	—	Git ref (branch/SHA)
`file`	string	Yes	File path containing the vulnerability (relative, no traversal)
`line`	integer	Yes	Line number of the finding
`repo`	string	Yes	GitHub repository name
`owner`	string	Yes	GitHub repository owner
`title`	string	Yes	Finding title from scan results
`token`	string	Yes	GitHub token with repo write access
`severity`	string	Yes	Finding severity
`description`	string	Yes	Finding description
`finding_type`	string	Yes	Finding type e.g. 'command_injection', 'sql_injection'
`recommendation`	string	Yes	Recommended fix from scan results

Parameters from the server's own tool schema.

RISK

Why auto_remediate is rated Medium

Creates a pull request modifying code, a reversible write action with significant blast radius.

From the tool's definition Creates a GitHub PR with the patched code

Risk signalsAccepts file system path (file) · Handles credentials or secrets (token) · High parameter count (11 properties)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs auto_remediate safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Mcp Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For auto_remediate, this is the rule to start with:

auto_remediate Rate-limited

auto_remediate stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "auto_remediate": {
      "limits": [
        {
          "counter": "auto_remediate_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Mcp Server, apply this rule, and every auto_remediate call is checked against it from then on.

FAQ

Questions about auto_remediate

What does the auto_remediate tool do? +

Generate an automated security fix for a specific finding. Creates a GitHub PR with the patched code. Verifies the fix with Level 1 SAST before opening the PR. Requires authentication, 3 credits, and ANTHROPIC_API_KEY. It is categorised as a Write tool in the Mcp Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does auto_remediate accept? +

auto_remediate accepts 11 parameters: ref, file, line, repo, owner, title, token, severity, description, finding_type, recommendation. Required: file, line, repo, owner, title, token, severity, description, finding_type, recommendation. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on auto_remediate? +

Register the Mcp Server MCP server in PolicyLayer and add a rule for auto_remediate: 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 Mcp Server. Nothing to install.

What risk level is auto_remediate? +

auto_remediate is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit auto_remediate? +

Yes. Add a rate_limit block to the auto_remediate 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 auto_remediate completely? +

Set action: deny in the PolicyLayer policy for auto_remediate. 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 auto_remediate? +

auto_remediate is provided by the Mcp Server MCP server (@graneth/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Mcp Server, and thousands of servers like it.

This server

All 4 Mcp Server tools →

Across the catalogue

The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →