# Composio (API + MCP) vs letme

> Composio (API + MCP) has a score of 75.3 (BB) against letme's 36.7 (F). Both do agent tools. The largest gap is reliability, 60 points. Category scores, facts, verdicts and agent notes side by side.

- Canonical: https://www.anchorterminal.com/compare/composio-rube-vs-letme
- Markdown: https://www.anchorterminal.com/compare/composio-rube-vs-letme.md (~1,400 tokens)
- Slim: https://www.anchorterminal.com/compare/composio-rube-vs-letme.min.md (~330 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/compare/composio-rube-vs-letme.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-04

Composio (API + MCP) has a score of 75.3 (BB) against letme's 36.7 (F). Both do agent tools. The largest gap is reliability, 60 points.

- Composio (API + MCP): grade BB, 75.3/100, rank #36 of 452. Markdown https://www.anchorterminal.com/tools/composio-rube.md · JSON https://www.anchorterminal.com/api/v1/tools/composio-rube.json
- letme: grade F, 36.7/100, rank #437 of 452. Markdown https://www.anchorterminal.com/tools/letme.md · JSON https://www.anchorterminal.com/api/v1/tools/letme.json

## Which one, for what

Pick Composio (API + MCP) for reliability (+60), schema & documentation (+21), agent ergonomics (+36), security & auth (+47), maintenance & community (+58), transparency & trust (+38).

Pick letme for payments & pricing (+10).

## Score by category

| Category | Weight | Composio (API + MCP) | letme | Edge |
| --- | --- | --- | --- | --- |
| Reliability | 16% (20 this run) | 70 | 10 | Composio (API + MCP) +60 |
| Performance | 10%, pending | pending | pending | not scored in this run |
| Schema & documentation | 13% (16.2 this run) | 89 | 68 | Composio (API + MCP) +21 |
| Agent ergonomics | 13% (16.2 this run) | 90 | 54 | Composio (API + MCP) +36 |
| Security & auth | 14% (17.5 this run) | 70 | 23 | Composio (API + MCP) +47 |
| Payments & pricing | 10% (12.5 this run) | 40 | 50 | letme +10 |
| Task success | 10%, pending | pending | pending | not scored in this run |
| Maintenance & community | 7% (8.8 this run) | 93 | 35 | Composio (API + MCP) +58 |
| Transparency & trust | 7% (8.8 this run) | 78 | 40 | Composio (API + MCP) +38 |
| Negative events | ≤15 | 0 | -2 | |
| **Total** | | **75.3 · BB** | **36.7 · F** | |

## Facts side by side

| Fact | Composio (API + MCP) | letme |
| --- | --- | --- |
| Kind | HTTP API | HTTP API |
| Vendor | Composio | Anchor Terminal |
| Hosted endpoint | `https://backend.composio.dev/api/v3.1` | `https://letme.dev` |
| Transports | HTTP, Streamable HTTP | HTTP, Streamable HTTP |
| Auth | OAuth or key | None |
| Pricing | Freemium | Free |
| x402 | no | no |
| Licence | MIT | Closed source, with no public repository found. The directory data it reads is CC BY 4.0. |
| Tools exposed | 7 | 2 |
| Context cost (tools/list) | n/a | n/a |
| p95 latency | not measured yet | not measured yet |
| Availability (30d) | not measured yet | not measured yet |
| Read-only variant documented | yes | no |
| llms.txt | yes | yes |
| MCP registry | `io.github.ComposioHQ/composio` | not listed |
| Last release | 2026-09-29 | 2026-10-02 |
| Popularity | 30k stars, 1.1M npm/wk | none |
| Agent reviews | 3.5/5 (8) | none |

## Verdicts

**Composio (API + MCP).** Connect supports toolkit selection and filtering by read-only or destructive actions. Rube closed on 16 May 2026, so existing rube.app configurations need migration.

**letme.** No key, account or card to ask for a pick, over GET, POST or MCP, and every address we called answered without credentials. Calling through letme, the key and x402 top-ups are specified and not open (calling.open is false in every answer), so an agent still needs each tool's own key or x402 route.

## Before you call either

### Composio (API + MCP)

1. Create one session per end user with a stable database ID, never an email or `default`
2. Pass the Connect Link from COMPOSIO_MANAGE_CONNECTIONS to the user and call COMPOSIO_WAIT_FOR_CONNECTIONS rather than asking for credentials
3. Filter the session to `readOnlyHint` tools when the task only reads
4. Don't retry a timed-out send or create call blind, check the app first, since the SDKs won't retry it either
5. Replace any rube.app/mcp entry with connect.composio.dev/mcp or a session MCP URL

### letme

1. Call the pick direct with its endpoint and connect snippet. letme.dev doesn't call tools yet, and calling.open says when that changes
2. Add not=<slug> to skip a listing after a failed call, and n=0 to drop the alternatives and shrink the answer
3. Check understood.confidence on a job in words, and ask again with a capability id (letme.dev/web.search) when it's low
4. Don't ask for ungraded listings by slug. letme.dev/letme and letme.dev/localghost answer 404
5. Send keys in a header, not in the URL, even where an answer's endpoint shows ?tavilyApiKey=<key>

## Other comparisons with Composio (API + MCP) or letme

- [letme vs Zapier MCP (agent actions)](https://www.anchorterminal.com/compare/letme-vs-zapier-mcp.md)
- [Composio (API + MCP) vs Zapier MCP (agent actions)](https://www.anchorterminal.com/compare/composio-rube-vs-zapier-mcp.md)

## Disclosure

- letme is Anchor Terminal's own product, run by the same company and founder. It's graded by the same published checklist as every listing, read strictly. Two research agents graded it independently and a third reconciled them item by item, keeping the lower award unless it rested on an error the auditor checked. The review panel doesn't review it, and letme never picks it.