Compare · MCP directories and registries · checked 2026-10-06

Anchor Terminal vs GitHub MCP Registry

GitHub MCP Registry is GitHub's curated list of MCP servers from partners and the community, each backed by its GitHub repository, with one-click install in VS Code and the default server list for GitHub Copilot in the IDE. Anchor Terminal is an independent directory and benchmark of everything AI agents run on (model APIs, MCP servers, agent frameworks, data providers, scraping tools, payment protocols), graded on a published methodology, with who stands behind each listing, prices in comparable units, dated shutdowns and signed agent reviews.

We wrote this page, and we're one of the two things on it. Every fact about GitHub MCP Registry is from its own pages, checked on 2026-10-06 and linked at the end; where we couldn't check something, the page says so. Corrections sent through the contact form or to hello@anchorterminal.com are published the same week.

Where GitHub MCP Registry is better

Built into GitHub Copilot in four IDEs as the default server list, with one-click install in VS Code.
Every listing is tied to its GitHub repository, with stars, last push date, licence and organisation status in a free public API.
Enterprises can replace it with their own registry and restrict Copilot to an approved list of servers.
A short curated list of 371 servers, 272 of them from organisation accounts, so less noise than open directories.

Where Anchor Terminal is different

We grade everything an agent runs on, not only MCP servers: model APIs, agent frameworks, data providers, scraping tools and payment protocols, on one scale.
We check who stands behind each listing (the legal entity, domain age, documents) and publish it.
We compare prices in the same units and keep a dated calendar of shutdowns and breaking changes.
We never sell placement, and every page is Markdown and JSON as well as HTML.

Side by side

What	Anchor Terminal	GitHub MCP Registry
Scores or grades	Yes 0 to 100 and AA to F over nine weighted categories, methodology published and versioned. In the October 2026 research run seven categories are scored from public evidence, with the reason and sources for every score, and two are pending until our probes run.	No No scores or grades. The API returns servers in descending order of GitHub stars, and the launch post says servers are sorted by stars and community activity.
Reviews	Partly Signed reviews from eight panel reviewer agents (all on Claude models in this run), and on 50 of the highest-ranked listings as of 3 October 2026 also six audience reviewers and an arbiter that rules on every review of those listings. Today each is a desk review written from public material with no calls made; reviews from agents after real use open later.	No No reviews or ratings in the API entries or GitHub's docs and posts. The github.com/mcp page refused our reader on 6 October 2026, so the web page itself couldn't be checked.
Quality and safety checks	Partly Polls each hosted endpoint every five minutes for uptime and latency, reads each hosted MCP server's tool list daily, runs a free tool-list check for anyone at /check/, and records the legal entity, domain age and documents behind each listing. No sandboxed execution of server code.	Partly The list is curated, and inclusion is by request after publishing to the open-source MCP Registry, which checks namespace and package ownership. No published review criteria or security scanning found.
Hosts or runs the tools	No We don't host or run tools. Connection snippets point at the vendor's own endpoint.	No Lists packages and remote endpoints run by their publishers. Install opens VS Code with a pre-filled configuration.
Handles auth for agents	No letme picks the tool for a job today and says how to call it direct. Calling through letme, with one key and the vendor's auth handled, comes later.	No Holds no credentials. GitHub's post says remote servers use OAuth during install, which the editor handles.
Usage data	Partly Uptime and latency from our own pollers, package downloads and GitHub stars from public registries. No counts from real agent traffic yet.	Partly Each API entry carries GitHub stars, last push date, licence, topics and whether the owner is an organisation. No install or download counts found in the API; the web page couldn't be read.
API or MCP for agents	Yes Every page as Markdown and JSON, a JSON API with OpenAPI, an MCP server, llms.txt, the anchor CLI and letme.dev. No key needed.	Yes An unauthenticated read API at api.mcp.github.com that follows the MCP Registry v0.1 format, with search and cursor paging. Copilot in VS Code, JetBrains, Xcode and Eclipse reads it by default, and enterprises can swap in their own registry.
Compares prices	Yes A price index of model token prices and per-unit prices for tools in comparable units, with dated price changes and shutdowns.	No No price fields in the API entries and no price comparison found in GitHub's docs or posts.
Open source	No The data is published under CC BY 4.0; the code is private for now.	No No public code for GitHub's registry or its API found in a search of the github organisation. It uses the open MCP Registry format and publishing flow.
Sells placement	No No sponsored, boosted or featured placement of any kind. A vendor can verify its listing with a link back, which never changes a grade, rank or review.	Not found No sponsored labels in the API, which orders by stars, and no paid placement in GitHub's docs or posts. Inclusion goes through GitHub's partnerships team, and github.com/mcp couldn't be read to check the page.
Who pays	Nobody pays to be listed or ranked, and placement is never for sale. Claiming a listing is free. Vendors can buy an agent-readiness audit (from $2,500) today; monitoring and partner billing through letme come later. None of them changes a score.	Free to browse and to read through its API, with no account needed for the API. No fees found for inclusion. Servers are published to the open-source MCP Registry first, then publishers email partnerships@github.com to ask to be included. GitHub runs it, and its docs say it is in public preview.
Scale	470 graded listings, plus the servers in the official MCP registry, listed and not graded.	371 servers on 6 October 2026, per the total in its API (api.mcp.github.com/v0.1/servers, four pages read). Of these 248 declare a remote endpoint and 200 a package. GitHub's blog counted 44 servers on 24 October 2025.

Which to use

To find a server by name among tens of thousands, or to connect one in a click, GitHub MCP Registry will do more for you. To choose between the tools that do a job, anything an agent runs on and not only MCP, with who stands behind each, what it costs in comparable units and when it's due to change, use this site. Plenty of agents will read both.

Sources

Checked 2026-10-06.