Mcp Gateway

io.github.titus-civicPublished by GitHub account titus-civicv1.0.0Updated Oct 24, 2026

Identity, authorization, audit trails, and revocable permissions for AI agents accessing MCP tools.

The publisher's own server: Nexus

VerifiedStreamable HTTPWeb executableDeveloper ToolsSecurity & Monitoring

Overview

AI-generated overview

Remote MCP gateway that adds agent identity, scoped tool permissions, audit logging and revocable access to AI tool calls.

What you can do
  • Connect an assistant to MCP tools through a permission layer that sits outside the agent
  • Authenticate agents with Civic-issued bearer tokens or OAuth and scope them to specific tools
  • Log every tool call with agent identity and timestamp for an audit trail
  • Revoke a token so an agent loses access immediately
  • Apply guardrails such as rate limits, approval workflows and deny lists through a configurator
  • Lock the endpoint to a named profile to scope it to a specific configuration
When to use it
Useful when an assistant calls sensitive tools such as email, calendar or databases and you need to restrict which tools it can reach, keep a record of what it did, and be able to cut off access quickly. Also suited to non-interactive agents that need token-based authentication instead of an interactive OAuth flow.
Requirements
A remote Streamable HTTP endpoint at app.civic.com; no local package needed. A Civic account to sign in and generate a bearer token, or OAuth handled by the client on first connection. Clients that use a bearer token pass it in an Authorization header. Network access to the gateway.
Before you install
The gateway holds credentials that control agent access: a bearer token grants whatever the token is scoped to, so store it carefully and revoke it when no longer needed. Guardrails and audit logs only cover calls routed through the gateway, and tool calls and their metadata are sent to Civic's hosted service. Review the configured deny lists and approval rules before relying on them.

Installation

In SourceWeft

  1. Open Mcp Gateway in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.titus-civic%2Fmcp-gateway/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "gateway": {
      "type": "http",
      "url": "https://app.civic.com/hub/mcp"
    }
  }
}

README

Civic MCP Gateway

Connecting AI Agents to tools and data via the Civic MCP Gateway gives builders access to guardrails, scoped permissions, audit trails, and revocable access when calling MCP tools. Civic separates the permission layer from the AI agent so they can't get around restrictions.

This repository contains integration metadata, configuration files, and client examples. The gateway itself runs at app.civic.com.


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. Civic fixes that:

  • Agent identity — agents authenticate with a Civic-issued bearer token
  • 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

MCP Endpoint

https://app.civic.com/hub/mcp

Transport: Streamable HTTP Auth: Bearer token (generated at app.civic.com)


Quickstart

1. Get a token

Sign in at app.civic.com and generate a bearer token from the onboarding flow.

2. Configure your MCP client

Claude Desktop — native Streamable HTTP:

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

json
{  "mcpServers": {    "civic": {      "url": "https://app.civic.com/hub/mcp"    }  }}

Claude Code — native HTTP transport (no bridge needed):

bash
claude mcp add --transport http civic https://app.civic.com/hub/mcp

Or for stdio via Hub Bridge:

bash
claude mcp add civic "npx @civic/hub-bridge"

Cursor — native Streamable HTTP:

Add to your Cursor MCP config:

json
{  "mcpServers": {    "civic": {      "url": "https://app.civic.com/hub/mcp"    }  }}

Cline (VS Code) — add to cline_mcp_settings.json:

json
{  "mcpServers": {    "civic": {      "url": "https://app.civic.com/hub/mcp",      "headers": {        "Authorization": "Bearer YOUR_CIVIC_TOKEN"      }    }  }}

Windsurf — native Streamable HTTP, no bridge required:

Add to ~/.codeium/windsurf/mcp_config.json:

json
{  "mcpServers": {    "civic": {      "serverUrl": "https://app.civic.com/hub/mcp"    }  }}

Windsurf handles OAuth automatically on first connection.

3. Optional: lock to a profile

Append ?profile=your-toolkit to scope the gateway to a specific configuration:

https://app.civic.com/hub/mcp?profile=your-toolkit

Automated agents (token-based auth)

For non-interactive agents that can't complete an OAuth flow, generate a bearer token at app.civic.com and pass it directly:

bash
curl -X POST https://app.civic.com/hub/mcp \  -H "Authorization: Bearer $CIVIC_TOKEN" \  -H "Content-Type: application/json" \  -d '{"jsonrpc":"2.0","method":"tools/list","id":1}'

Install from a registry

Example use cases

Use caseWhat Civic adds
Gmail guardrails & auditBlock outbound sends with secrets, redact PII from email content, log every send
Google Calendar guardrails & auditPrevent event deletion, restrict to business hours, block external attendees
PostgreSQL guardrails & auditBlock destructive queries, enforce read-only access, redact sensitive columns

Documentation

Full documentation at docs.civic.com


Working example

See civicteam/nexus-demo for a full client integration using Next.js, federated auth, and MCP tool visualization.


License

MIT

Source: README.md at commit 2ec8eef

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Civic integrations