# Find the best tools for agents, and how we decide what to return (slim)

> Vlad Cealicu on how Anchor Terminal finds the best tools for agents. Nine categories scored from public evidence with the sources dated, grades from AA to F, what a search returns and in what order, how letme picks one tool by a published rule, what we never do, and why it matters when an agent pays for a wrong pick in tokens, failed calls and money.

- Full: https://www.anchorterminal.com/blog/find-the-best-tools-for-agents.md (~2,500 tokens) · this version ~1,430 tokens · JSON https://www.anchorterminal.com/blog/find-the-best-tools-for-agents.json · canonical https://www.anchorterminal.com/blog/find-the-best-tools-for-agents
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-07
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

By Vlad Cealicu, 7 November 2026. 1,099 words, about 5 min to read.

- 1,491: graded listings, scored on the same nine categories
- 207: of them agent-ready, graded BB or better
- 2,222: indexed listings, with facts and our own checks and no score

What we hold, read on 6 November 2026. Sources [2] and [4].

The directories that rank agent tools mostly rank them by GitHub stars, package downloads or how often a tool gets called through one proxy, and those numbers say what's popular without saying whether the tool answers at three in the morning, whether a model can make sense of its descriptions, how many tokens it costs before the first useful call or whether an agent can pay for it without a human [[1]](#ref-1).

## What we score

Every graded listing is scored on nine categories that add up to 100 points, weighted by what breaks agents in practice.

Category weights, out of 100

| Category | Weight |
| --- | --- |
| Reliability | 16 |
| Security and auth | 14 |
| Schema and documentation | 13 |
| Agent ergonomics | 13 |
| Payments and pricing | 10 |
| Performance (pending) | 10 |
| Task success (pending) | 10 |
| Maintenance and community | 7 |
| Transparency and trust | 7 |

Each series has a zero-based scale.

Research agents read each listing's public evidence, status pages and incident history, rate-limit and error docs, API references and OpenAPI files, MCP tool definitions in the source, pricing pages, terms, security pages, changelogs and repositories, and every listing carries at least four sources with the date each was read, a confidence and a list of what we couldn't check [[1]](#ref-1).

The total maps to a grade from AA down to F, and BB or better is what we call agent-ready, meaning you can give the tool to an autonomous agent as long as you read the caveats on its page [[1]](#ref-1).

Graded listings by grade

| Grade | Listings |
| --- | --- |
| AA | 1 |
| A | 22 |
| BB | 184 |
| B | 352 |
| C | 379 |
| D | 247 |
| E | 169 |
| F | 137 |

Each series has a zero-based scale.

## What a search returns

A search for a job comes back in three groups, in this order, and every row says which group it's in.

In order

1. **Graded listings** (scored). ranked by score, each with its grade, auth, price, whether it's up now and one line on why it's above the next [[3]](#ref-3)
2. **Indexed listings** (checked). facts and our own checks from public catalogues, with no score, grade or rank [[4]](#ref-4)
3. **The official MCP registry** (as published). other servers, described the way their publishers describe them [[3]](#ref-3)

An indexed listing has to clear a bar first, a hosted endpoint that answered tools/list in the last fortnight, at least 1,000 weekly npm or PyPI downloads or 300 GitHub stars, or a vendor's own verified domain, and of the 57,183 servers in the official MCP registry on 6 November, 2,000 cleared it [[4]](#ref-4).

The filters for what a company needs (an agent can start alone, no card, data in the EU, doesn't train on your data) answer yes, no or unknown for every listing, and the answer says how many it left out as each, because an agent can't tell "no" from "we haven't researched it" unless we tell it [[3]](#ref-3).

## How letme picks one

letme is the part that gives an agent a single answer.

## What we don't do

Rankings are never for sale, and reports are paid while rankings aren't [[1]](#ref-1).

## Why it matters

An agent pays for a wrong pick in tokens, in failed calls and in money, and it usually finds out halfway through a job.

Performance and task success are still pending until the probes and the task suites run, and the research on what a first call takes and what a company needs covered 107 of the 1,491 graded listings on 6 November [[2]](#ref-2), with more added since.

---

More in [Inside Anchor Terminal](https://www.anchorterminal.com/blog/inside/index.md)

- Older: [What an agent asks before it picks a tool, and what a site should answer](https://www.anchorterminal.com/blog/what-an-agent-asks-before-it-picks-a-tool.md)
- Newer: [AI is eating bureaucracy for the sake of bureaucracy](https://www.anchorterminal.com/blog/ai-is-eating-bureaucracy.md)
- All posts: https://www.anchorterminal.com/blog/index.md

Anchor Terminal grades the tools AI agents run on, with a source for every score.

## References

Read on 6 and 7 November 2026.

[1] Anchor Terminal, 2026. The benchmark, methodology 0.7. Source for the case against popularity rankings and the 2,006-character tool description, the nine categories and their weights, the evidence read and the five rules, negative events, the grade bands and agent-ready, the rules for our own products and for Anthropic's listings, the principle that reports are paid and rankings aren't, and what we learned at CryptoCompare.

[2] Anchor Terminal, 2026. The directory as JSON, read on 6 November 2026. Source for the 1,491 graded listings, the count at each grade, the 207 agent-ready and the 107 with setup or compliance research.

[3] Anchor Terminal, 2026. For agents, the search, its filters and weights.

[4] Anchor Terminal, 2026. The index of listings built from public catalogues, read on 6 November 2026. Source for the bar an indexed listing clears, the 57,183 servers in the official MCP registry, the 2,000 that cleared it and the 2,222 indexed listings.

[5] Anchor Terminal, 2026. letme.