AuthorityPrompt MCP Server
Enables Gemini to read verified company facts, sources, provenance, and confidence from AuthorityPrompt for any published company domain.
README
AuthorityPrompt for Gemini CLI
Companies have an official website for humans. They don't have an official identity for AI. AuthorityPrompt is that identity — and this extension lets you manage your own company's identity from Gemini CLI.
You sign in with your AuthorityPrompt account. Gemini then works with your company's data: verified facts, sources, AIO readiness, LLM visibility. Each account sees only its own companies.
Install
gemini extensions install https://github.com/authorityprompt/gemini-authorityprompt-mcp
On first install Gemini CLI asks whether to trust the current workspace — answer
Y. The first time a tool runs, your browser opens the AuthorityPrompt consent
screen. After you approve, the token is managed by Gemini CLI; nothing is stored
in this repository.
You need an AuthorityPrompt account: https://authorityprompt.com
Use
Ask in plain language:
Which account am I connected as?
List my companies.
Run an AIO readiness audit.
Add https://example.com/about as a source for my company.
What do LLMs currently say about us, and where does it disagree with our facts?
What it can do
Read your account and companies, pull the canonical profile, verified facts, sources with provenance and confidence, run AIO readiness audits and LLM visibility checks, and — with your consent — publish and repair company facts.
Writes are explicit: the tools that change data are separate from the ones that read it, and the OAuth scopes you grant decide which are available.
Permissions
The extension requests only what it needs:
| Scope | Purpose |
|---|---|
profile:read |
identify the connected account |
companies:read |
list your companies |
company_profile:read |
read canonical profile, facts, sources |
company_profile:write |
publish or repair facts, add sources |
reports:read |
read audit and visibility reports |
aio:run |
run AIO readiness audits |
generators:run |
generate llms.txt, JSON-LD, answer blocks |
visibility:check |
check what LLMs say about the company |
Revoke access any time from your AuthorityPrompt account settings.
How it works
This extension is a thin manifest. It points Gemini CLI at the AuthorityPrompt MCP endpoint:
https://authorityprompt.com/api/v1/integrations/gemini/mcp
There is no local server and no dependencies to install. The endpoint requires
OAuth 2.0; Gemini CLI discovers the authorization server from the 401
response, registers itself dynamically (RFC 7591) and runs the flow with PKCE.
Links
- Website: https://authorityprompt.com
- Privacy: https://authorityprompt.com/privacy
- Terms: https://authorityprompt.com/terms
- Support: hello@authorityprompt.com
License
MIT — see LICENSE.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.