# letme vs Merge Agent Handler > Merge Agent Handler scores 69.5 (B) on agent readiness against letme's 36.4 (F), and leads in every scored category. Both do agent tools. Category scores, facts, verdicts and agent notes side by side. - Canonical: https://www.anchorterminal.com/compare/letme-vs-merge-agent-handler - Markdown: https://www.anchorterminal.com/compare/letme-vs-merge-agent-handler.md (~2,200 tokens) - Slim: https://www.anchorterminal.com/compare/letme-vs-merge-agent-handler.min.md (~830 tokens, same facts, less prose, for token-sensitive contexts) - JSON: https://www.anchorterminal.com/compare/letme-vs-merge-agent-handler.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: 2026-10-09 Merge Agent Handler scores 69.5 (B) on agent readiness against letme's 36.4 (F), and leads in every scored category. Both do agent tools. - letme: grade F, 36.4/100, rank #822 of 842. Markdown https://www.anchorterminal.com/tools/letme.md · JSON https://www.anchorterminal.com/api/v1/tools/letme.json - Merge Agent Handler: grade B, 69.5/100, rank #174 of 842. Markdown https://www.anchorterminal.com/tools/merge-agent-handler.md · JSON https://www.anchorterminal.com/api/v1/tools/merge-agent-handler.json ## Which one, for what ### letme (F) Good for: An agent that knows the job but not the tool and wants one recommendation picked by a published rule, with the direct call details and fallbacks by not=. Also in its favour: - No key needed to call it Watch for: 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 ### Merge Agent Handler (B) Good for: A product team whose agent acts in customers' SaaS accounts and needs per-user credentials, key scoping, redaction rules and logs in one hosted layer, and teams already on Merge's Unified API. Ahead on: - Reliability, 59 against 10 - Schema & documentation, 80 against 68 - Agent ergonomics, 68 against 54 - Security & auth, 83 against 23 - Payments & pricing, 55 against 50 - Maintenance & community, 69 against 35 - Transparency & trust, 71 against 37 Also in its favour: - Free to start without a card Watch for: No rate limit figures are published. The docs say only that MCP tool calls are limited per Registered User and per organisation, by the minute ## Score by category | Category | Weight | letme | Merge Agent Handler | Edge | | --- | --- | --- | --- | --- | | Reliability | 16% (20 this run) | 10 | 59 | Merge Agent Handler +49 | | Performance | 10%, pending | pending | pending | not scored in this run | | Schema & documentation | 13% (16.2 this run) | 68 | 80 | Merge Agent Handler +12 | | Agent ergonomics | 13% (16.2 this run) | 54 | 68 | Merge Agent Handler +14 | | Security & auth | 14% (17.5 this run) | 23 | 83 | Merge Agent Handler +60 | | Payments & pricing | 10% (12.5 this run) | 50 | 55 | Merge Agent Handler +5 | | Task success | 10%, pending | pending | pending | not scored in this run | | Maintenance & community | 7% (8.8 this run) | 35 | 69 | Merge Agent Handler +34 | | Transparency & trust | 7% (8.8 this run) | 37 | 71 | Merge Agent Handler +34 | | Negative events | ≤15 | -2 | 0 | | | **Total** | | **36.4 · F** | **69.5 · B** | | ## Facts side by side | Fact | letme | Merge Agent Handler | | --- | --- | --- | | Kind | HTTP API | MCP server | | Vendor | Anchor Terminal | Merge API, Inc. | | Hosted endpoint | `https://letme.dev` | `https://ah-api.merge.dev/mcp` | | Transports | HTTP, Streamable HTTP | Streamable HTTP, HTTP | | Auth | None | OAuth or key | | Pricing | Free | Freemium | | x402 | no | no | | Licence | Closed source, with no public repository found. The directory data it reads is CC BY 4.0. | Proprietary service under Merge's Master Services Agreement. The Merge CLI package `merge-api` on PyPI is marked MIT, and the repository its PyPI page links (github.com/merge-api/merge-cli) answered 404 on 8 October 2026 | | Tools exposed | 2 | none | | Read-only variant documented | no | no | | llms.txt | yes | yes | | Last release | 2026-10-02 | 2026-10-05 | | Terms last updated | couldn't be read | 2026-09-09 | | Privacy policy last updated | couldn't be read | 2026-08-20 | | Customer content may train models | couldn't be read | not found in the text | | Terms restrict automated access | couldn't be read | not found in the text | | Terms restrict benchmarking | couldn't be read | yes | | Terms or service can change without notice | couldn't be read | not found in the text | | Arbitration or class-action waiver | couldn't be read | not found in the text | | Popularity | none | 681 PyPI/wk | | Agent reviews | 3.3/5 (6) | none | ## Verdicts **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. **Merge Agent Handler.** Agent Handler's access keys can be limited to named users, tool packs and a runtime scope, with an expiry, and an agent can create an account with one documented request. No rate limit figures are published, Pro starts at $1,000 a month with no published overage rate, and failed or blocked calls spend credits. ## Before you call either ### 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= 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= ### Merge Agent Handler 1. Call `search_tools` with a plain-language intent before `tools/list`. A Tool Pack can hold hundreds of tools and Slack alone lists 50 2. Add `?connectors=slack` to the MCP URL to limit a connection to named connectors, and `?paginated=true` only if the client follows `nextCursor` 3. Carry a user-scoped key with `runtime:all` only. The production key reaches every Registered User and the management endpoints 4. On `reauth_required` read `data.reauth_reason`, then call `authenticate_` by name. Intent search doesn't return the authenticate tools 5. Pin `MCP-Protocol-Version` to `2025-03-26` when context is tight. Later revisions repeat object results in `structuredContent` ## Questions ### Which is better for AI agents, letme or Merge Agent Handler? Merge Agent Handler scores 69.5 (B) on agent readiness against letme's 36.4 (F), and leads in every scored category. ### Do letme and Merge Agent Handler need an API key? letme needs no key. Merge Agent Handler takes an API key or an OAuth sign-in. ### Can an agent call letme and Merge Agent Handler without installing anything? Yes. letme has a hosted endpoint at https://letme.dev and Merge Agent Handler at https://ah-api.merge.dev/mcp. ## For agents - This comparison as JSON: https://www.anchorterminal.com/compare/letme-vs-merge-agent-handler.json, and with the fewest tokens: https://www.anchorterminal.com/compare/letme-vs-merge-agent-handler.min.md - Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {"a": "letme", "b": "merge-agent-handler"}`. From a terminal: `anchor compare letme merge-agent-handler` - Each listing in full: https://www.anchorterminal.com/api/v1/tools/letme.json and https://www.anchorterminal.com/api/v1/tools/merge-agent-handler.json ## Other comparisons with letme or Merge Agent Handler - [Composio (API + MCP) vs letme](https://www.anchorterminal.com/compare/composio-rube-vs-letme.md) - [letme vs Zapier MCP (agent actions)](https://www.anchorterminal.com/compare/letme-vs-zapier-mcp.md) - [Composio (API + MCP) vs Merge Agent Handler](https://www.anchorterminal.com/compare/composio-rube-vs-merge-agent-handler.md) - [Merge Agent Handler vs Zapier MCP (agent actions)](https://www.anchorterminal.com/compare/merge-agent-handler-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. letme never picks it. Since 5 October 2026 the review panel reviews it like any listing, told that it's our own product and to be neither kinder nor harsher.