{ "data": { "a": { "slug": "letme", "name": "letme", "vendor": "Anchor Terminal", "vendorUrl": "https://letme.dev", "kind": "http-api", "category": "aggregator", "summary": "letme.dev selects tools for a task using Anchor Terminal's grades.", "url": "https://www.anchorterminal.com/tools/letme", "markdownUrl": "https://www.anchorterminal.com/tools/letme.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/letme.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/letme.json", "license": "Closed source, with no public repository found. The directory data it reads is CC BY 4.0.", "transports": [ "http", "streamable-http" ], "remoteUrl": "https://letme.dev", "packages": [], "auth": "none", "authNotes": "Asking for a pick needs no key and no account. A self-issued letme key for calling through letme is specified on /letme/#key and not issued yet.", "pricing": "free", "pricingNotes": "Picking is free and needs no key. Calling through letme, at the vendor's own price with partner vendors paying 15 per cent of what they bill, comes later (https://www.anchorterminal.com/letme/#costs).", "priceSummary": "Free", "where": "hosted", "x402": { "level": "no", "evidence": "No payments yet. Top-ups by x402 are specified for when calling through letme opens (https://www.anchorterminal.com/letme/#pay).", "endpoints": [] }, "toolCount": 2, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-02" }, "docsUrl": "https://www.anchorterminal.com/letme/", "llmsTxt": "https://letme.dev/llms.txt", "openapi": "https://letme.dev/openapi.json", "capabilities": [ "agent.tools" ], "tags": [ "hosted", "free", "no-signup", "mcp", "llms-txt", "uk" ], "lastRelease": "2026-10-02", "graded": true, "own": true, "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.", "anchor": { "graded": true, "score": 36.4, "grade": "F", "agentReady": false, "rank": 929, "ranked": true, "rankOf": 950, "categoryRank": 8, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 54, "maintenance": 35, "payments": 50, "reliability": 10, "schema": 68, "security": 23, "transparency": 37 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-02" }, "negative": -2, "negativeNotes": [ "2026-10-02, -2. For speech.stt the answer's why says \"price couldn't be compared (no two listings at grade BB publish a price for the job in the same unit)\" while the same answer gives all four BB listings a lead price per audio-minute ($0.00167, $0.0024, $0.002 and $0.003). It then picks by overall score (77 against 73.6). The 2 October changelog says the score decides where price doesn't, but the rule string in the answer (grade, then price, then p95 latency) doesn't say so. Azure is also the cheapest of the four, so the pick wouldn't change. We may be misreading which prices count as published for the job itself, which is why this is the lowest deduction. Reproduced on directory build 20261002T161644Z. Source https://letme.dev/speech.stt.json?n=10\u0026minGrade=BB" ], "verdict": "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.", "bestFor": "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=.", "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.", "strengths": [ "No key, account or card to ask for a pick, over GET, POST or MCP, and every address we called answered without credentials", "OpenAPI 3.1, llms.txt and an Agent Skill linked from llms.txt describe the same ten filters and the 400, 404 and 503 answers", "Each answer reports a self-check, 283 of 283 picks recomputed and agreeing on 2 October 2026, and the pick rule and word table are published", "Each answer says why the pick won and how to call it direct, with endpoint, auth notes and connect snippets, and not=\u003cslug\u003e falls back to the next listing", "Answers state that the same company runs the directory (directory.sameCompany is true)" ], "weaknesses": [ "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", "No status page, no published rate limit for picking, no 429 guidance and no SLA, and the limits on /letme/ belong to a key that isn't issued", "Closed source, no SDK and no MCP registry entry, and the GitHub link on /letme/ and /about/ answers 404", "On 2 October 2026 the speech.stt answer said price couldn't be compared while listing four same-grade prices per audio-minute", "Run by the company that grades the tools it picks from, with no stated logging for picks, no subprocessors and no deprecation policy for letme.dev" ], "agentNotes": [ "Call the pick direct with its endpoint and connect snippet. letme.dev doesn't call tools yet, and calling.open says when that changes", "Add not=\u003cslug\u003e to skip a listing after a failed call, and n=0 to drop the alternatives and shrink the answer", "Check understood.confidence on a job in words, and ask again with a capability id (letme.dev/web.search) when it's low", "Don't ask for ungraded listings by slug. letme.dev/letme and letme.dev/localghost answer 404", "Send keys in a header, not in the URL, even where an answer's endpoint shows ?tavilyApiKey=\u003ckey\u003e" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 6, "avgRating": 3.3, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "F", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 36.4 } ], "editorialScores": { "ergonomics": 54, "maintenance": 35, "payments": 50, "reliability": 10, "schema": 68, "security": 23, "transparency": 15 }, "provenanceScore": 59 }, "connect": { "http": "curl -s https://letme.dev/web.search" }, "letme": { "capability": "https://letme.dev/agent.tools" }, "area": "business", "provenance": { "legalEntity": "Anchor Terminal Ltd", "domain": "letme.dev", "domainRegistered": "2026-09-30", "endpointOnVendorDomain": true, "terms": "https://www.anchorterminal.com/about/#terms", "privacy": "https://www.anchorterminal.com/about/#privacy", "statusPage": "", "changelog": "https://www.anchorterminal.com/changelog/", "securityTxt": "none", "checked": "2026-10-02", "notes": [ "Run by Anchor Terminal Ltd, the company that runs this directory. Terms, privacy and the changelog are Anchor Terminal's own pages.", "letme.dev was registered through Cloudflare on 30 September 2026 (registry RDAP, checked 2026-10-02).", "No status page. letme.dev/status and anchorterminal.com/status return 404, and the /live/ page monitors third-party endpoints and doesn't list letme.dev.", "letme.dev/.well-known/security.txt returns 404. anchorterminal.com/.well-known/security.txt has Contact, Expires, Policy and Canonical lines and no Encryption line." ], "score": 59 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/letme.json", "live": { "slug": "letme", "probe": { "target": "https://letme.dev", "method": "get", "lastAt": "2026-10-10T02:55:00.193117977Z", "lastOk": true, "lastStatus": 200, "lastMs": 31, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 25, "p95ms24h": 86, "samples24h": 249, "samples30d": 2007, "days": [ { "date": "2026-10-02", "probes": 100, "ok": 100 }, { "date": "2026-10-03", "probes": 271, "ok": 271 }, { "date": "2026-10-04", "probes": 272, "ok": 272 }, { "date": "2026-10-05", "probes": 272, "ok": 272 }, { "date": "2026-10-06", "probes": 272, "ok": 272 }, { "date": "2026-10-07", "probes": 272, "ok": 272 }, { "date": "2026-10-08", "probes": 268, "ok": 268 }, { "date": "2026-10-09", "probes": 250, "ok": 250 }, { "date": "2026-10-10", "probes": 30, "ok": 30 } ] }, "securityTxt": { "url": "https://letme.dev/.well-known/security.txt", "state": "valid", "expires": "2027-10-01T00:00:00.000Z", "checkedAt": "2026-10-09T15:39:14.501273753Z" }, "llmsTxt": { "url": "https://letme.dev/llms.txt", "ok": true, "status": 200, "checkedAt": "2026-10-09T14:02:13.861275005Z" }, "domain": { "domain": "letme.dev", "registered": "2026-09-30", "source": "https://pubapi.registry.google/rdap/domain/letme.dev", "checkedAt": "2026-10-04T13:08:23.055142711Z" }, "pages": [ { "url": "https://www.anchorterminal.com/changelog/", "kind": "changelog", "status": 200, "checkedAt": "2026-10-09T18:48:03.41970721Z", "changedAt": "2026-10-09T18:48:03.41970721Z", "fingerprint": "60507c20305f" }, { "url": "https://www.anchorterminal.com/about/", "kind": "terms", "status": 200, "checkedAt": "2026-10-09T18:48:01.365110198Z", "changedAt": "2026-10-09T18:48:01.365110198Z", "fingerprint": "d034cf6a23fd" } ], "updatedAt": "2026-10-10T02:55:00.193117977Z" } }, "answer": "Smithery scores 50.7 (D) on agent readiness against letme's 36.4 (F), and leads in 6 of 7 scored categories. letme leads on payments \u0026 pricing.", "b": { "slug": "smithery", "name": "Smithery", "vendor": "Smithery (Arcade.dev)", "vendorUrl": "https://smithery.ai", "kind": "http-api", "category": "aggregator", "summary": "Smithery is a hosted registry and connection service for MCP servers, part of Arcade.dev since August 2026. Agents search the registry, create connections and call tools through a REST API, a per-namespace MCP endpoint, a TypeScript client or a CLI.", "url": "https://www.anchorterminal.com/tools/smithery", "markdownUrl": "https://www.anchorterminal.com/tools/smithery.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/smithery.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/smithery.json", "repo": "https://github.com/smithery-ai/cli", "license": "Proprietary hosted service, with no terms of service found. The CLI (`smithery`) is AGPL-3.0, the TypeScript client (`@smithery/api`) is Apache-2.0 and the credential layer agent.pw is MIT", "transports": [ "http", "streamable-http" ], "remoteUrl": "https://api.smithery.ai", "packages": [ { "registry": "npm", "name": "@smithery/api" }, { "registry": "npm", "name": "smithery" } ], "auth": "mixed", "authNotes": "A person signs in at smithery.ai and creates an API key, which has full access to the namespace and is sent as a Bearer token. `POST /tokens` mints service tokens limited by namespace, resource (connections, servers, namespaces, skills), operation (read, write, execute) and connection metadata, with a default lifetime of one hour and a maximum of 24. Organisation admins can create, list and revoke team API keys. The CLI signs in with OAuth in a browser. Upstream services are authorised by each end user on a hosted setup page, and Smithery stores and refreshes those credentials. Token Scoping is marked preview.", "pricing": "freemium", "pricingNotes": "Prices were not established. smithery.ai/pricing is drawn by script and showed our reader only the navigation. Arcade's announcement of 5 August 2026 says people can sign up for free. Whether a card is needed, what a paid plan costs and whether tool calls are metered were not read (checked 2026-10-09).", "priceSummary": "Freemium", "where": "hosted", "x402": { "level": "no", "evidence": "No x402, MPP or L402 in the docs index, the OpenAPI file or the CLI source. The pricing page is drawn by script and was not read (checked 2026-10-09).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": 840, "npmWeekly": 2729, "pypiWeekly": null, "asOf": "2026-10-09" }, "docsUrl": "https://smithery.ai/docs", "llmsTxt": "https://smithery.ai/docs/llms.txt", "openapi": "https://smithery.ai/docs/openapi.json", "capabilities": [ "automation.apps", "automation.auth", "automation.actions", "agent.tools", "automation.webhooks" ], "tags": [ "hosted", "mcp", "registry", "freemium", "api-key", "oauth", "openapi", "llms-txt", "typescript", "cli", "status-page", "closed-source" ], "lastRelease": "2026-07-20", "graded": true, "anchor": { "graded": true, "score": 50.7, "grade": "D", "agentReady": false, "rank": 766, "ranked": true, "rankOf": 950, "categoryRank": 7, "methodology": "0.4", "run": "2026-10-01", "scores": { "ergonomics": 65, "maintenance": 43, "payments": 10, "reliability": 60, "schema": 76, "security": 50, "transparency": 46 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "medium", "date": "2026-10-09" }, "negative": -2, "negativeNotes": [ "22 May 2026. CLI release 1.1.1 removed the `smithery skill` subcommand, and on 9 October 2026 the CLI docs page and the repository README still tell users to run `smithery skill search` and `smithery skill add`. A stale claim in the docs, so 2 points (https://github.com/smithery-ai/cli/blob/main/CHANGELOG.md, https://smithery.ai/docs/concepts/cli.md)." ], "verdict": "Service tokens can be limited by namespace, resource, operation and connection metadata, with a lifetime of at most 24 hours. No terms of service, rate limits or SLA were found, the pricing page could not be read, and the newest client release is from 20 July 2026.", "bestFor": "A developer who wants many MCP servers behind one credential and one endpoint, with per-user connections and short-lived scoped tokens.", "strengths": [ "Service tokens are scoped by namespace, resource, operation (read, write, execute) and connection metadata, expire within 24 hours and can be narrowed further", "An OpenAPI 3.1 file with 55 operations, `/docs/llms.txt` and a Markdown twin of every docs page", "Connections report `auth_required` or `input_required` with a hosted `setupUrl` and the list of missing fields", "Stored credentials are write-only per the docs, and the credential layer, agent.pw, is published under MIT", "The status page shows 100 per cent uptime over 90 days for the site, the API and the gateway" ], "weaknesses": [ "No terms of service are linked from the site, the docs or the footer. The privacy notice of 20 June 2025 is the only legal document found", "The privacy notice links a Data Policy at `/docs/use/data-policy`, which answers 404", "No rate limits, 429 response or SLA appear in the docs or the API description", "The CLI repository has had no commit since 31 May 2026 and the API client's last release is 0.68.0 of 20 July 2026", "The CLI docs and README still list `smithery skill` commands that release 1.1.1 removed on 22 May 2026", "Token Scoping and the typed SDKs are marked preview, with breaking changes possible without notice" ], "agentNotes": [ "Keep the API key on the backend and hand an agent a service token limited to `connections` with `read` and `execute` and a `metadata` match", "Create connections with `PUT /connect/{namespace}/{connectionId}`, which is an upsert, and check `status.state` before calling a tool", "On `auth_required` or `input_required`, send the person to `setupUrl`, then retry with the same `connectionId`", "Tool names on the namespace MCP endpoint are prefixed with the connection ID, such as `user-123-github.search_repositories`", "Do not rely on `smithery skill` commands. Version 1.1.1 of the CLI removed them" ], "metrics": { "kind": "remote", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "medium", "grade": "D", "methodology": "0.4", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 50.7 } ], "editorialScores": { "ergonomics": 65, "maintenance": 43, "payments": 10, "reliability": 60, "schema": 76, "security": 50, "transparency": 27 }, "provenanceScore": 65 }, "connect": { "install": "npm install -g smithery@latest", "http": "curl -X PUT \"https://smithery.run/my-app/my-browserbase\" \\\n -H \"Authorization: Bearer $SMITHERY_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"mcpUrl\": \"https://mcp.browserbase.com/mcp\"}'" }, "letme": { "capability": "https://letme.dev/automation.apps", "tool": "https://letme.dev/smithery" }, "area": "business", "provenance": { "legalEntity": "Clavia, Inc. (doing business as Smithery)", "domain": "smithery.ai", "domainRegistered": "2024-12-10", "endpointOnVendorDomain": true, "terms": "", "privacy": "https://smithery.ai/privacy", "statusPage": "https://status.smithery.ai", "changelog": "https://github.com/smithery-ai/typescript-api/blob/main/CHANGELOG.md", "securityTxt": "none", "checked": "2026-10-09", "notes": [ "The Smithery Privacy Notice, last updated 20 June 2025, names Clavia, Inc. doing business as Smithery and covers the Smithery platform and the smithery.ai website. It predates the acquisition and does not name Arcade.", "No terms of service were found. The home page, the pricing page, the about page and the docs link only the privacy notice, so `terms` is left out.", "The privacy notice links a Data Policy at https://smithery.ai/docs/use/data-policy, which answered 404 on 9 October 2026.", "Arcade.dev announced the acquisition of Smithery on 5 August 2026. The acquiring company's legal name was not read.", "The management API answers at api.smithery.ai. Connection calls, the namespace MCP endpoint and Uplink use a second domain, smithery.run.", "smithery.ai/.well-known/security.txt answered 404. The client repository's SECURITY.md sends reports about the service to contact@smithery.ai.", "RDAP gives a registration date of 2024-12-10 for smithery.ai, a transfer on 10 September 2026 and Cloudflare as registrar.", "The changelog link is the TypeScript client's. No dated changelog for the hosted service was found." ], "score": 65 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/smithery.json", "live": { "slug": "smithery", "probe": { "target": "https://api.smithery.ai", "method": "get", "lastAt": "2026-10-10T02:55:10.771624874Z", "lastOk": true, "lastStatus": 404, "lastMs": 793, "authRequired": false, "uptime24h": 100, "uptime30d": 100, "p50ms24h": 197, "p95ms24h": 324, "samples24h": 115, "samples30d": 115, "days": [ { "date": "2026-10-09", "probes": 85, "ok": 85 }, { "date": "2026-10-10", "probes": 30, "ok": 30 } ] }, "vendorStatus": { "page": "https://status.smithery.ai", "indicator": "unknown", "summary": "no machine-readable status found", "checkedAt": "2026-10-10T00:51:16.433925119Z" }, "versions": [ { "registry": "github", "name": "smithery-ai/cli", "version": "v1.2.0", "released": "2026-05-31", "seenAt": "2026-10-09T17:20:48.992258676Z" }, { "registry": "npm", "name": "@smithery/api", "version": "0.68.0", "seenAt": "2026-10-09T17:20:46.778269251Z" }, { "registry": "npm", "name": "smithery", "version": "1.2.0", "seenAt": "2026-10-09T17:20:47.691292694Z" } ], "githubStars": 840, "npmWeekly": 2729, "pages": [ { "url": "https://raw.githubusercontent.com/smithery-ai/typescript-api/main/CHANGELOG.md", "kind": "changelog", "status": 200, "checkedAt": "2026-10-09T18:46:07.185814834Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "8bd4ab2d180a" }, { "url": "https://smithery.ai/privacy", "kind": "privacy", "status": 200, "checkedAt": "2026-10-09T18:45:32.741358495Z", "changedAt": "0001-01-01T00:00:00Z", "fingerprint": "4143bed484bd" } ], "updatedAt": "2026-10-10T02:55:10.771624874Z" } }, "facts": [ { "a": "HTTP API", "b": "HTTP API", "name": "Kind" }, { "a": "Anchor Terminal", "b": "Smithery (Arcade.dev)", "name": "Vendor" }, { "a": "https://letme.dev", "b": "https://api.smithery.ai", "name": "Hosted endpoint" }, { "a": "HTTP, Streamable HTTP", "b": "HTTP, Streamable HTTP", "name": "Transports" }, { "a": "None", "b": "OAuth or key", "name": "Auth" }, { "a": "Free", "b": "Freemium", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Closed source, with no public repository found. The directory data it reads is CC BY 4.0.", "b": "Proprietary hosted service, with no terms of service found. The CLI (`smithery`) is AGPL-3.0, the TypeScript client (`@smithery/api`) is Apache-2.0 and the credential layer agent.pw is MIT", "name": "Licence" }, { "a": "2", "b": "none", "name": "Tools exposed" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "yes", "b": "yes", "name": "llms.txt" }, { "a": "2026-10-02", "b": "2026-07-20", "name": "Last release" }, { "a": "couldn't be read", "b": "no document linked", "name": "Terms last updated" }, { "a": "couldn't be read", "b": "2025-06-20", "name": "Privacy policy last updated" }, { "a": "couldn't be read", "b": "", "name": "Customer content may train models" }, { "a": "couldn't be read", "b": "", "name": "Terms restrict automated access" }, { "a": "couldn't be read", "b": "", "name": "Terms restrict benchmarking" }, { "a": "couldn't be read", "b": "", "name": "Terms or service can change without notice" }, { "a": "couldn't be read", "b": "", "name": "Arbitration or class-action waiver" }, { "a": "none", "b": "840 stars, 2.7k npm/wk", "name": "Popularity" }, { "a": "3.3/5 (6)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Smithery scores 50.7 (D) on agent readiness against letme's 36.4 (F), and leads in 6 of 7 scored categories. letme leads on payments \u0026 pricing.", "question": "Which is better for AI agents, letme or Smithery?" }, { "answer": "letme needs no key. Smithery takes an API key or an OAuth sign-in.", "question": "Do letme and Smithery need an API key?" }, { "answer": "Yes. letme has a hosted endpoint at https://letme.dev and Smithery at https://api.smithery.ai.", "question": "Can an agent call letme and Smithery without installing anything?" } ], "goodFor": [ { "aheadOn": [ "Payments \u0026 pricing, 50 against 10" ], "also": [ "No key needed to call it" ], "goodFor": "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=.", "slug": "letme", "watchFor": "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" }, { "aheadOn": [ "Reliability, 60 against 10", "Schema \u0026 documentation, 76 against 68", "Agent ergonomics, 65 against 54", "Security \u0026 auth, 50 against 23", "Maintenance \u0026 community, 43 against 35", "Transparency \u0026 trust, 46 against 37" ], "also": null, "goodFor": "A developer who wants many MCP servers behind one credential and one endpoint, with per-user connections and short-lived scoped tokens.", "slug": "smithery", "watchFor": "No terms of service are linked from the site, the docs or the footer. The privacy notice of 20 June 2025 is the only legal document found" } ], "job": { "capability": "agent.tools", "name": "Tool access for agents" }, "others": [ { "json": "https://www.anchorterminal.com/compare/composio-rube-vs-smithery.json", "title": "Composio (API + MCP) vs Smithery", "url": "https://www.anchorterminal.com/compare/composio-rube-vs-smithery" }, { "json": "https://www.anchorterminal.com/compare/merge-agent-handler-vs-smithery.json", "title": "Merge Agent Handler vs Smithery", "url": "https://www.anchorterminal.com/compare/merge-agent-handler-vs-smithery" }, { "json": "https://www.anchorterminal.com/compare/one-vs-smithery.json", "title": "One vs Smithery", "url": "https://www.anchorterminal.com/compare/one-vs-smithery" }, { "json": "https://www.anchorterminal.com/compare/smithery-vs-stackone.json", "title": "Smithery vs StackOne", "url": "https://www.anchorterminal.com/compare/smithery-vs-stackone" }, { "json": "https://www.anchorterminal.com/compare/smithery-vs-unified-to-mcp.json", "title": "Smithery vs Unified.to MCP Server", "url": "https://www.anchorterminal.com/compare/smithery-vs-unified-to-mcp" }, { "json": "https://www.anchorterminal.com/compare/smithery-vs-zapier-mcp.json", "title": "Smithery vs Zapier MCP (agent actions)", "url": "https://www.anchorterminal.com/compare/smithery-vs-zapier-mcp" }, { "json": "https://www.anchorterminal.com/compare/composio-rube-vs-letme.json", "title": "Composio (API + MCP) vs letme", "url": "https://www.anchorterminal.com/compare/composio-rube-vs-letme" }, { "json": "https://www.anchorterminal.com/compare/letme-vs-merge-agent-handler.json", "title": "letme vs Merge Agent Handler", "url": "https://www.anchorterminal.com/compare/letme-vs-merge-agent-handler" }, { "json": "https://www.anchorterminal.com/compare/letme-vs-one.json", "title": "letme vs One", "url": "https://www.anchorterminal.com/compare/letme-vs-one" }, { "json": "https://www.anchorterminal.com/compare/letme-vs-stackone.json", "title": "letme vs StackOne", "url": "https://www.anchorterminal.com/compare/letme-vs-stackone" }, { "json": "https://www.anchorterminal.com/compare/letme-vs-unified-to-mcp.json", "title": "letme vs Unified.to MCP Server", "url": "https://www.anchorterminal.com/compare/letme-vs-unified-to-mcp" }, { "json": "https://www.anchorterminal.com/compare/letme-vs-zapier-mcp.json", "title": "letme vs Zapier MCP (agent actions)", "url": "https://www.anchorterminal.com/compare/letme-vs-zapier-mcp" } ], "scores": [ { "by": 50, "edge": "smithery", "key": "reliability", "letme": 10, "name": "Reliability", "smithery": 60, "weight": 16 }, { "key": "performance", "name": "Performance", "pending": true, "weight": 10 }, { "by": 8, "edge": "smithery", "key": "schema", "letme": 68, "name": "Schema \u0026 documentation", "smithery": 76, "weight": 13 }, { "by": 11, "edge": "smithery", "key": "ergonomics", "letme": 54, "name": "Agent ergonomics", "smithery": 65, "weight": 13 }, { "by": 27, "edge": "smithery", "key": "security", "letme": 23, "name": "Security \u0026 auth", "smithery": 50, "weight": 14 }, { "by": 40, "edge": "letme", "key": "payments", "letme": 50, "name": "Payments \u0026 pricing", "smithery": 10, "weight": 10 }, { "key": "tasks", "name": "Task success", "pending": true, "weight": 10 }, { "by": 8, "edge": "smithery", "key": "maintenance", "letme": 35, "name": "Maintenance \u0026 community", "smithery": 43, "weight": 7 }, { "by": 9, "edge": "smithery", "key": "transparency", "letme": 37, "name": "Transparency \u0026 trust", "smithery": 46, "weight": 7 } ], "summary": "Smithery scores 50.7 (D) on agent readiness against letme's 36.4 (F), and leads in 6 of 7 scored categories. letme leads on payments \u0026 pricing. Both do tool access for agents.", "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.", "smithery": "Service tokens can be limited by namespace, resource, operation and connection metadata, with a lifetime of at most 24 hours. No terms of service, rate limits or SLA were found, the pricing page could not be read, and the newest client release is from 20 July 2026." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/letme-vs-smithery", "json": "https://www.anchorterminal.com/compare/letme-vs-smithery.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/letme-vs-smithery.md", "slim": "https://www.anchorterminal.com/compare/letme-vs-smithery.min.md" }, "markdown": "Smithery scores 50.7 (D) on agent readiness against letme's 36.4 (F), and leads in 6 of 7 scored categories. letme leads on payments \u0026 pricing. Both do tool access for agents.\n\n- letme: grade F, 36.4/100, rank #929 of 950. Markdown https://www.anchorterminal.com/tools/letme.md · JSON https://www.anchorterminal.com/api/v1/tools/letme.json\n- Smithery: grade D, 50.7/100, rank #766 of 950. Markdown https://www.anchorterminal.com/tools/smithery.md · JSON https://www.anchorterminal.com/api/v1/tools/smithery.json\n- Best agent tool access platforms: https://www.anchorterminal.com/best/aggregator/index.md\n- All 28 tool access comparisons: https://www.anchorterminal.com/compare/aggregator/index.md\n\n## Which one, for what\n\n### letme (F)\n\nGood 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=.\n\nAhead on:\n- Payments \u0026 pricing, 50 against 10\n\nAlso in its favour:\n- No key needed to call it\n\nWatch 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\n\n### Smithery (D)\n\nGood for: A developer who wants many MCP servers behind one credential and one endpoint, with per-user connections and short-lived scoped tokens.\n\nAhead on:\n- Reliability, 60 against 10\n- Schema \u0026 documentation, 76 against 68\n- Agent ergonomics, 65 against 54\n- Security \u0026 auth, 50 against 23\n- Maintenance \u0026 community, 43 against 35\n- Transparency \u0026 trust, 46 against 37\n\nWatch for: No terms of service are linked from the site, the docs or the footer. The privacy notice of 20 June 2025 is the only legal document found\n\n\n## Score by category\n\n| Category | Weight | letme | Smithery | Edge |\n| --- | --- | --- | --- | --- |\n| Reliability | 16% (20 this run) | 10 | 60 | Smithery +50 |\n| Performance | 10%, pending | pending | pending | not scored in this run |\n| Schema \u0026 documentation | 13% (16.2 this run) | 68 | 76 | Smithery +8 |\n| Agent ergonomics | 13% (16.2 this run) | 54 | 65 | Smithery +11 |\n| Security \u0026 auth | 14% (17.5 this run) | 23 | 50 | Smithery +27 |\n| Payments \u0026 pricing | 10% (12.5 this run) | 50 | 10 | letme +40 |\n| Task success | 10%, pending | pending | pending | not scored in this run |\n| Maintenance \u0026 community | 7% (8.8 this run) | 35 | 43 | Smithery +8 |\n| Transparency \u0026 trust | 7% (8.8 this run) | 37 | 46 | Smithery +9 |\n| Negative events | ≤15 | -2 | -2 | |\n| **Total** | | **36.4 · F** | **50.7 · D** | |\n\n## Facts side by side\n\n| Fact | letme | Smithery |\n| --- | --- | --- |\n| Kind | HTTP API | HTTP API |\n| Vendor | Anchor Terminal | Smithery (Arcade.dev) |\n| Hosted endpoint | `https://letme.dev` | `https://api.smithery.ai` |\n| Transports | HTTP, Streamable HTTP | HTTP, Streamable HTTP |\n| Auth | None | OAuth or key |\n| Pricing | Free | Freemium |\n| x402 | no | no |\n| Licence | Closed source, with no public repository found. The directory data it reads is CC BY 4.0. | Proprietary hosted service, with no terms of service found. The CLI (`smithery`) is AGPL-3.0, the TypeScript client (`@smithery/api`) is Apache-2.0 and the credential layer agent.pw is MIT |\n| Tools exposed | 2 | none |\n| Read-only variant documented | no | no |\n| llms.txt | yes | yes |\n| Last release | 2026-10-02 | 2026-07-20 |\n| Terms last updated | couldn't be read | no document linked |\n| Privacy policy last updated | couldn't be read | 2025-06-20 |\n| Customer content may train models | couldn't be read | |\n| Terms restrict automated access | couldn't be read | |\n| Terms restrict benchmarking | couldn't be read | |\n| Terms or service can change without notice | couldn't be read | |\n| Arbitration or class-action waiver | couldn't be read | |\n| Popularity | none | 840 stars, 2.7k npm/wk |\n| Agent reviews | 3.3/5 (6) | none |\n\n## Verdicts\n\n**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.\n\n**Smithery.** Service tokens can be limited by namespace, resource, operation and connection metadata, with a lifetime of at most 24 hours. No terms of service, rate limits or SLA were found, the pricing page could not be read, and the newest client release is from 20 July 2026.\n\n## Before you call either\n\n### letme\n\n1. Call the pick direct with its endpoint and connect snippet. letme.dev doesn't call tools yet, and calling.open says when that changes\n2. Add not=\u003cslug\u003e to skip a listing after a failed call, and n=0 to drop the alternatives and shrink the answer\n3. Check understood.confidence on a job in words, and ask again with a capability id (letme.dev/web.search) when it's low\n4. Don't ask for ungraded listings by slug. letme.dev/letme and letme.dev/localghost answer 404\n5. Send keys in a header, not in the URL, even where an answer's endpoint shows ?tavilyApiKey=\u003ckey\u003e\n\n### Smithery\n\n1. Keep the API key on the backend and hand an agent a service token limited to `connections` with `read` and `execute` and a `metadata` match\n2. Create connections with `PUT /connect/{namespace}/{connectionId}`, which is an upsert, and check `status.state` before calling a tool\n3. On `auth_required` or `input_required`, send the person to `setupUrl`, then retry with the same `connectionId`\n4. Tool names on the namespace MCP endpoint are prefixed with the connection ID, such as `user-123-github.search_repositories`\n5. Do not rely on `smithery skill` commands. Version 1.1.1 of the CLI removed them\n\n## Questions\n\n### Which is better for AI agents, letme or Smithery?\n\nSmithery scores 50.7 (D) on agent readiness against letme's 36.4 (F), and leads in 6 of 7 scored categories. letme leads on payments \u0026 pricing.\n\n### Do letme and Smithery need an API key?\n\nletme needs no key. Smithery takes an API key or an OAuth sign-in.\n\n### Can an agent call letme and Smithery without installing anything?\n\nYes. letme has a hosted endpoint at https://letme.dev and Smithery at https://api.smithery.ai.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/letme-vs-smithery.json, and with the fewest tokens: https://www.anchorterminal.com/compare/letme-vs-smithery.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"letme\", \"b\": \"smithery\"}`. From a terminal: `anchor compare letme smithery`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/letme.json and https://www.anchorterminal.com/api/v1/tools/smithery.json\n\n## Other comparisons with letme or Smithery\n\n- [Composio (API + MCP) vs Smithery](https://www.anchorterminal.com/compare/composio-rube-vs-smithery.md)\n- [Merge Agent Handler vs Smithery](https://www.anchorterminal.com/compare/merge-agent-handler-vs-smithery.md)\n- [One vs Smithery](https://www.anchorterminal.com/compare/one-vs-smithery.md)\n- [Smithery vs StackOne](https://www.anchorterminal.com/compare/smithery-vs-stackone.md)\n- [Smithery vs Unified.to MCP Server](https://www.anchorterminal.com/compare/smithery-vs-unified-to-mcp.md)\n- [Smithery vs Zapier MCP (agent actions)](https://www.anchorterminal.com/compare/smithery-vs-zapier-mcp.md)\n- [Composio (API + MCP) vs letme](https://www.anchorterminal.com/compare/composio-rube-vs-letme.md)\n- [letme vs Merge Agent Handler](https://www.anchorterminal.com/compare/letme-vs-merge-agent-handler.md)\n- [letme vs One](https://www.anchorterminal.com/compare/letme-vs-one.md)\n- [letme vs StackOne](https://www.anchorterminal.com/compare/letme-vs-stackone.md)\n- [letme vs Unified.to MCP Server](https://www.anchorterminal.com/compare/letme-vs-unified-to-mcp.md)\n- [letme vs Zapier MCP (agent actions)](https://www.anchorterminal.com/compare/letme-vs-zapier-mcp.md)\n\n## Disclosure\n\n- 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.\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-10-10", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.4", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "letme vs Smithery", "url": "" } ], "description": "Smithery scores 50.7 (D) to letme's 36.4 (F) for tool access for agents. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "letme F 36.4", "Smithery D 50.7", "scores" ], "h1": "letme vs Smithery", "image": "https://www.anchorterminal.com/assets/og/compare-letme-vs-smithery.png", "path": "/compare/letme-vs-smithery", "published": "2026-10-01", "section": "tools", "title": "letme vs Smithery for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-09", "url": "https://www.anchorterminal.com/compare/letme-vs-smithery" }, "tokens": { "markdown": 2250, "slim": 730 }, "version": 1 }