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

Anchor Terminal vs MCP Market

MCP Market is a directory of MCP servers, agent skills and MCP clients with GitHub-star leaderboards, plus a Hub that hosts and connects servers for agents and a marketplace for paid skills. Run by Sitka Labs, a Canadian company. 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 Market 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 Market is better

Hosts servers deployed from GitHub, npm, PyPI or Docker, which a directory like ours doesn't do.
Handles OAuth and API-key connections with per-user credentials, and bundles chosen tools from several servers behind one MCP endpoint.
Lists agent skills as well as servers (368,597 stated on 4 October 2026) and lets creators sell skills from their own storefront.
Organisations see tool-call volume, errors and latency from their own agents' traffic through the Hub.

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 Market
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 Top 100 server leaderboard and the daily lists of newly found servers are ranked by GitHub stars, as their pages state. No quality score, grade or 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 the server, skill and seller pages read.
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 Submissions are reviewed for inclusion, with no published criteria. A $29 listing adds an 'Official badge', and the submit page doesn't say what it certifies. No security scanning found, and the Hub docs tell users to deploy only sources they trust.
Hosts or runs the tools	No We don't host or run tools. Connection snippets point at the vendor's own endpoint.	Yes The Hub hosts servers deployed from GitHub, npm, PyPI or Docker (Pro plan and up) and connects catalogue servers. The docs don't say where deployed servers run or how they're isolated.
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.	Yes The Hub connects servers through OAuth or API-key flows, with per-user credentials so a shared toolkit doesn't share secrets. Toolkits put chosen tools from several servers behind one MCP endpoint. How credentials are stored isn't described in the docs.
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 Listings show GitHub stars, not usage, and skill listings show an unlabelled count. Hub organisations see tool-call volume, errors and latency for their own servers. No public usage counts found.
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.	Partly Hub users get an MCP endpoint per server or toolkit, and a plugin syncs skills and tools to Claude Code, Claude Desktop, Codex and Cursor. Organisation API tokens exist, but no API reference and no public catalogue API or MCP server were found. Its robots.txt blocks /api/.
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. Paid skills show only their own price.
Open source	No The data is published under CC BY 4.0; the code is private for now.	No No public code for the site, catalogue or Hub was found on its site, in its docs or in a GitHub search.
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 Server pages carry display ads labelled Advertisement, and the footer has an 'Advertise with us' link with no published rates. A $29 listing adds an Official badge and 24-hour listing, while free listings get 'Standard placement'. No criteria for its 52 Featured servers found.
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. Hub plans are Free, Pro ($19 a month) and Team ($149 a month for five users, then $9 a user), each with a monthly credit allowance the docs don't define. Creators can pay $29 once to be listed within 24 hours with an Official badge, or wait an average of 4 to 6 weeks free. Skill sellers set their own prices ($19 one-off on the premium skills read), and no commission is published. Server pages carry display ads, with no published rates.
Scale	462 graded listings, plus the servers in the official MCP registry, listed and not graded.	48,423 MCP servers ('updated 2 hours ago') on mcpmarket.com and 368,597 agent skills ('updated just now') on mcpmarket.com/tools/skills, both on 4 October 2026, plus 19 MCP clients. Its submit page gives lower round figures, 35K+ servers and 200K+ skills.

Which to use

To find a server by name among tens of thousands, or to connect one in a click, MCP Market 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.