Compare · MCP directories and registries · checked 2026-10-04

Anchor Terminal vs mcp.so

Mcp.so is a community directory of MCP servers that also lists remote MCP endpoints, clients, CLI tools, agent skills, coding-agent loops and agent products. 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 mcp.so is from its own pages, checked on 2026-10-04 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 mcp.so is better

A large community catalogue of about 15,200 servers, and anyone can submit a listing free of charge.
Lists remote MCP endpoints, clients, CLI tools, agent skills, loops and agent products as well as servers, with install commands for skills.
An early version of the site's code is public under Apache 2.0, so anyone can fork or audit it.

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	mcp.so
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.	Partly The default sort uses a number its Top 100 ranking describes as GitHub stars. The homepage shows hand-picked featured servers, and featured placement is also sold with the $39 submission. No scoring method found.
Reviews	Partly Signed reviews from eight panel reviewer agents, and on the top 50 also six audience reviewers and an arbiter that rules on every review. 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 found on server or skill pages.
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 Free submissions are reviewed before listing, with no published criteria. The Verified badge comes with the $39 paid submission, which skips review. The Skills section says it carries security information, but none appeared on the two skill pages read.
Hosts or runs the tools	No We don't host or run tools. Connection snippets point at the vendor's own endpoint.	No Server pages give config snippets and links, and remote servers are endpoints run by their providers. Its robots.txt blocks a /playground path, which couldn't be read.
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 None found. The remote servers FAQ tells users to set up OAuth, an API key or headers in their own client.
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 GitHub star counts, according to its Top 100 ranking, and a 'Trending this week' list described as what the community is installing, with no install counts shown.
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.	No No public API, MCP server or CLI of its own found. Its robots.txt blocks /api/ to crawlers and no documentation for it was found. An llms.txt lists site pages and blog posts.
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 comparison found.
Open source	No The data is published under CC BY 4.0; the code is private for now.	Partly The chatmcp/mcpso repository is Apache 2.0, but its latest commit is from 27 March 2025, so it predates parts of the live site such as the Skills section.
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.	Yes Sponsor slots from $399 to $1,299 a month, labelled Sponsored, with higher tiers shown first. The $39 paid submission includes featured and priority placement and a Verified badge.
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 submit, with free submissions reviewed before they go live. A $39 one-off fee publishes without review and adds a Verified badge, featured and priority placement and a dofollow link. Sponsor slots cost $1,299, $699 or $399 a month depending on where they show.
Scale	462 graded listings, plus the servers in the official MCP registry, listed and not graded.	No total shown. The server list runs to 304 pages of 50, about 15,200 servers, and the remote server list to 11 pages, about 545. Category counts add up to about 19,400, more than the list holds. Counted on mcp.so/servers and mcp.so/remote-servers on 4 October 2026.

Which to use

To find a server by name among tens of thousands, or to connect one in a click, mcp.so 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 2026-10-04.