# civic-mcp-gateway

> Use this tool when you need to securely manage AI agent access to multiple tools and resources, solving problems of unauthorized access and lack of audit trails. The civic-mcp-gateway provides a single connector to access 85 tools with scoped permissions, audit trails, and revocable access. It takes in agent authentication requests and outputs verified identities, permissions, and access controls, making it ideal for use cases requiring secure and controlled AI agent interactions.

Canonical page: https://skillsregistry.net/skills/civic-civic-mcp-gateway  
JSON: https://api.skillsregistry.net/v1/skills/civic-civic-mcp-gateway

## Description

Give your AI agents a verified identity, scoped permissions, audit trails, and revocable access when calling MCP tools. This repository contains integration metadata, configuration files, and client examples. The gateway itself runs at [app.civic.com](https://app.civic.com).

Access 85 tools, 1000+ guardrails and configure 4000+ parameters via a single connector. 

## What it does

Without an identity layer, any AI agent can call any MCP tool with no record of who authorized it, what it accessed, or how to revoke its access.

With Civic you get:

- **Agent identity** — agents authenticate with a Civic-issued bearer token into 80+ tools
- **Scoped permissions** — grant agents access to specific tools only
- **Audit trail** — every tool call is logged with agent identity and timestamp
- **Revocable access** — revoke a token and the agent loses access immediately
- **Guardrails** — rate limits, approval workflows, and deny lists via the configurator

## Trust

- **Trust score (0–1):** 0.30
- **Verification tier:** unverified
- **Last scanned:** 2026-08-24

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** media
- **Updated:** 2026-08-24

## Source

- **Source listing:** [Smithery](https://smithery.ai/server/civic/civic-mcp-gateway)

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "civic-civic-mcp-gateway"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/civic-civic-mcp-gateway` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/civic-civic-mcp-gateway/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt