// SCAN REPORT

Ghe Mcp Gateway

21 tools. 5 can modify or destroy data without limits.

5 write tools that can modify data. Rate limits recommended.

Last updated: 2 Jul 2026

5 can modify or destroy data

16 read-only

21 tools total

Community server · catalogue entry verified 02/07/2026

How to control Ghe Mcp Gateway ↓

TOOL MAP

What Ghe Mcp Gateway exposes to your agents

Read (16) Write / Execute (5) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Ghe Mcp Gateway tools

Execute · High graphql_query Although GraphQL queries are often read-only, GraphQL also supports mutations that can create, modify, or delete data. Write · Medium resolve_secret_scanning_alert This tool modifies the state of a secret-scanning alert by resolving it. Write · High set_branch_protection This tool modifies repository settings reversibly by applying or updating branch protection policies. Write · High set_repo_collaborator_permission This tool modifies access control permissions by adding or updating collaborator roles on repositories.

5 of Ghe Mcp Gateway's 21 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Ghe Mcp Gateway

PolicyLayer is an MCP gateway — it sits between your AI agents and Ghe Mcp Gateway, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "resolve_secret_scanning_alert": {
    "limits": [
      {
        "counter": "resolve_secret_scanning_alert_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_branch_protection": {
    "limits": [
      {
        "counter": "get_branch_protection_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Ghe Mcp Gateway — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON GHE MCP GATEWAY →

Instant setup, no code required.

FULL CATALOGUE

All 21 Ghe Mcp Gateway tools

EXECUTE 1 tools

Execute graphql_query Run an arbitrary GraphQL query against GitHub's v4 API.

WRITE 4 tools

Write resolve_secret_scanning_alert Resolve a secret-scanning alert. WRITE OPERATION. Write set_branch_protection Apply a baseline branch-protection policy. WRITE OPERATION. Write set_repo_collaborator_permission Add or update a collaborator's permission on a repo. WRITE OPERATION. Write set_team_repo_permission Grant or update a team's permission on a repo. WRITE OPERATION.

READ 16 tools

Read get_branch_protection Get the branch-protection configuration for a branch (404 -> unprotected). Read get_org_audit_log Query an organization's audit log (requires org-owner token w/ read:audit_log). Read get_org_ruleset Get the full definition of a single org ruleset (rules, conditions, bypass actors). Read get_repo_permission Get a user's effective permission level on a repo (admin/write/read/none). Read get_repository Get full details for a single repository (settings, visibility, permissions). Read list_code_scanning_alerts List CodeQL/code-scanning alerts for a repo. state: open | closed | dismissed | fixed. Read list_dependabot_alerts List Dependabot vulnerability alerts. state: open | dismissed | fixed | auto_dismissed. Read list_org_rulesets List organization-level rulesets (the modern, scalable branch-protection model). Read list_org_webhooks List organization-level webhooks (events, active state, target URL). Read list_organization_members List members of an organization. role: all | admin | member. Read list_repo_collaborators List collaborators on a repo with their permission level. Read list_repositories List repositories for an org or user. Read list_secret_scanning_alerts List secret-scanning alerts for a repo, or for an org if repo is omitted. Read list_team_members List members of a team. role: all | maintainer | member. Read list_team_repos List repositories a team can access, with the team's permission on each. Read list_teams List all teams in an organization (slug, name, privacy, parent).

FAQ

Questions about Ghe Mcp Gateway

How do I prevent bulk modifications through Ghe Mcp Gateway? +

The Ghe Mcp Gateway server has 4 write tools including resolve_secret_scanning_alert, set_branch_protection, set_repo_collaborator_permission. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Ghe Mcp Gateway.

How many tools does the Ghe Mcp Gateway MCP server expose? +

21 tools across 2 categories: Read, Write. 16 are read-only. 5 can modify, create, or delete data.

How do I enforce a policy on Ghe Mcp Gateway? +

Register the Ghe Mcp Gateway MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Ghe Mcp Gateway tool call.

Deterministic rules across all 21 Ghe Mcp Gateway tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON GHE MCP GATEWAY →

Instant setup, no code required.

21 Ghe Mcp Gateway tools catalogued and risk-classified — across an index of 43,000+ MCP servers.