# Agent tool access: app actions and authentication for agents

> 3 agent tool access ranked by the Anchor benchmark. Leader Composio (API + MCP) (BB). Services that hand an agent ready-made actions across thousands of apps, with the OAuth connections and credentials handled for you. Compared on action coverage, how authorisation works per end user, what the agent sees in its context, logs and price per call. Workflow builders are compared separately.

- Canonical: https://www.anchorterminal.com/categories/aggregator
- Markdown: https://www.anchorterminal.com/categories/aggregator.md (~1,250 tokens)
- Slim: https://www.anchorterminal.com/categories/aggregator.min.md (~280 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/categories/aggregator.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

Services that hand an agent ready-made actions across thousands of apps, with the OAuth connections and credentials handled for you. Compared on action coverage, how authorisation works per end user, what the agent sees in its context, logs and price per call. Workflow builders are compared separately.

- Tools ranked: 3 · agent-ready (BB or better): 1 · accept x402: 0 · hosted endpoints: 3 · desk reviews by the panel: 10
- JSON: https://www.anchorterminal.com/api/v1/tools.json (list) · https://www.anchorterminal.com/api/v1/rankings.json (ranked) · https://www.anchorterminal.com/api/v1/x402.json (payable) · https://www.anchorterminal.com/api/v1/capabilities.json (by capability)
- Grades run AA, A, BB, B, C, D, E, F · methodology: https://www.anchorterminal.com/benchmark/

- Capabilities in this category: automation.apps, automation.auth, automation.actions, agent.tools
- https://letme.dev/automation.apps picks the top-graded tool in this list and says how to call it direct; calling through letme comes later (https://www.anchorterminal.com/letme/index.md)

## Ranking

| # | Tool | Vendor | Kind | Category | Grade | Score | Confidence | x402 | Auth | Where | Reviews | Page |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |
| 36 | Composio (API + MCP) | Composio | HTTP API | Tool access | BB | 75.3 | medium | no | OAuth or key | hosted | 3.5/5 (8) | https://www.anchorterminal.com/tools/composio-rube.md |
| 280 | Zapier MCP (agent actions) | Zapier | MCP server | Tool access | C | 58.4 | medium | no | OAuth or key | hosted | 2.5/5 (2) | https://www.anchorterminal.com/tools/zapier-mcp.md |
| 437 | letme | Anchor Terminal | HTTP API | Tool access | F | 36.7 | medium | no | None | hosted | none | https://www.anchorterminal.com/tools/letme.md |

Scores are from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/), with Performance and Task success pending. p95 latency and context cost come from our probes, which haven't run yet.

## Summaries

### 36. Composio (API + MCP), BB (75.3)

Tool access and per-user authentication for agents across 1,000+ apps. 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.

- Page: https://www.anchorterminal.com/tools/composio-rube · Markdown: https://www.anchorterminal.com/tools/composio-rube.md · JSON: https://www.anchorterminal.com/api/v1/tools/composio-rube.json
- Capabilities: automation.apps, automation.auth, automation.actions, agent.tools, automation.webhooks · endpoint: `https://backend.composio.dev/api/v3.1`

### 280. Zapier MCP (agent actions), C (58.4)

Hosted MCP server that lets agents discover and run actions across apps connected to the user's Zapier account. 16 meta-tools in agentic mode, or managed mode with only the actions you pick. Connection tokens are long-lived and the docs allow them in the URL query string.

- Page: https://www.anchorterminal.com/tools/zapier-mcp · Markdown: https://www.anchorterminal.com/tools/zapier-mcp.md · JSON: https://www.anchorterminal.com/api/v1/tools/zapier-mcp.json
- Capabilities: automation.apps, automation.auth, automation.actions, agent.tools · endpoint: `https://mcp.zapier.com/api/v1/connect`

### 437. letme, F (36.7)

letme.dev selects tools for a task using Anchor Terminal's grades. 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.

- Page: https://www.anchorterminal.com/tools/letme · Markdown: https://www.anchorterminal.com/tools/letme.md · JSON: https://www.anchorterminal.com/api/v1/tools/letme.json
- Capabilities: agent.tools · endpoint: `https://letme.dev`

## How we test this category

The same task across email, CRM and a database, driven by an agent through each service. We compare connection setup, how each end user authorises, action coverage, retries, logs and the cost per completed run. This test hasn't run yet, so Task success is pending and the grades here come from the categories assessed from public evidence.