# Clay > Clay is a go-to-market data and automation platform that searches its own database of companies and people and runs enrichment across 150+ data providers. Agents use it through the Public API v0, the clay CLI and a coding-agent plugin. - Canonical: https://www.anchorterminal.com/tools/clay - Markdown: https://www.anchorterminal.com/tools/clay.md (~5,850 tokens) - Slim: https://www.anchorterminal.com/tools/clay.min.md (~1,380 tokens, same facts, less prose, for token-sensitive contexts) - JSON: https://www.anchorterminal.com/tools/clay.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: 2026-10-14 ## Overview **Grade C · 57.7/100 · rank #633 of 1076 · #8 in Lead & company data · not agent-ready · confidence medium** ## Assessment A documented Public API with an OpenAPI spec, llms.txt and plan-capped search, plus a JSON-first CLI released several times a fortnight, give agents Clay's people search and multi-provider enrichment. Keys have no scopes, the Claude Code plugin auto-approves most CLI calls, and the privacy policy dates from 2020. ## Facts | Field | Value | | --- | --- | | Vendor | Clay Labs Inc. (https://www.clay.com) | | Kind | HTTP API | | Category | Lead & company data (https://www.anchorterminal.com/categories/lead-data) | | Transport | HTTP | | Endpoint | `https://api.clay.com/public/v0` | | Auth | OAuth or key · The Public API takes a personal API key in the clay-api-key header, tied to a Clay user and their workspace access, created in the app, with the CLI (clay api-keys create) or by an agent through the plugin. The CLI signs in with OAuth in a browser or with a device code (clay login --device), one workspace per sign-in. Custom functions need API or MCP access switched on per function (https://developers.clay.com/public-api/authentication). | | Pricing | Freemium ($0.05 / credit) · Free plan with 100 data credits and 500 actions a month. Launch from $167 a month and Growth from $446 a month on the plan cards, while the FAQ on the same page says $185 and $495. Data credits start at $0.05 and actions at under a cent. Failed enrichments aren't charged. The FAQ lists Clay API access under Enterprise, while the developer docs give search limits for Free, Trial and paid plans (https://www.clay.com/pricing, https://developers.clay.com/searches, checked 2026-10-14). | | x402 | No · No x402, MPP or L402 in the developer docs, the OpenAPI spec or the pricing page (checked 2026-10-14). | | Licence | Proprietary service under the Clay Terms of Service. The agent plugin repository carries no licence file | | Source | https://github.com/clay-run/agent-plugins | | Docs | https://developers.clay.com | | llms.txt | https://developers.clay.com/llms.txt | | Last release | 2026-10-06 | | Public API | https://api.clay.com/public/v0, 16 operations in OpenAPI 3, clay-api-key header | | Routines | Clay-managed functions (work email, phone, company data, tech stack, funding and more) and custom functions, run on 1 to 100 items or as a batch over a JSONL upload, results polled with 202 until done, or by webhook | | Search limits | Free 50 per request and 100 per 30 days. Trial 10,000 for the trial. Paid 500 per request and 1,000,000 per 30 days. Enterprise 10,000,000 per 30 days. HTTP 402 when exceeded | | CLI and plugin | clay CLI 1.9.0 with plugin 2.32.0 (6 October 2026) for Claude Code, Codex and Cursor. JSON output, exit code 4 for rate limits | | Tables | Structured queries on known tables, Enterprise only, with no list-tables endpoint | | Certifications | SOC 2 Type II, ISO 27001 and ISO 42001 per the pricing page. security.txt valid to 31 July 2027 | | MCP | Clay MCP for sales reps in Claude and ChatGPT, described on clay.com/mcp with no public endpoint or tool reference | | Capabilities | lead.search, lead.enrichment, email.finder, data.company | | Tags | hosted, freemium, api-key, openapi, llms-txt, cli, closed-source, lead-search, enrichment, soc2, webhooks | | JSON | https://www.anchorterminal.com/api/v1/tools/clay.json | ## Score breakdown (methodology v0.4, October 2026 research run) Assessed 2026-10-14 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: medium. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. "This run" is each category's share of the 100 points. | Category | Weight | This run | Score (0–100) | Points | | --- | --- | --- | --- | --- | | Reliability | 16% | 20 | 45 | 9.0 | | Performance | 10% | pending | pending | n/a | | Schema & documentation | 13% | 16.2 | 84 | 13.7 | | Agent ergonomics | 13% | 16.2 | 66 | 10.7 | | Security & auth | 14% | 17.5 | 48 | 8.4 | | Payments & pricing | 10% | 12.5 | 30 | 3.8 | | Task success | 10% | pending | pending | n/a | | Maintenance & community | 7% | 8.8 | 75 | 6.6 | | Transparency & trust (editorial 28, provenance 99) | 7% | 8.8 | 64 | 5.6 | | Negative events | up to −15 | up to −15 | none recorded | 0 | | **Total** | | | | **57.7 → C** | ### Why each score - Reliability 45: Graded with the hosted lines on the Public API. status.clay.com exists but answered with a bot check, so we couldn't confirm components (10 of 20). No readable history (5). A per-workspace request limit with no number, and published search-result caps per plan (8 of 15). 429 with Retry-After and X-RateLimit headers, backoff with jitter, and retry guidance only when a request is safe to retry. No idempotency keys (12 of 15). The terms set a 99.0 per cent monthly uptime target with credits for six-hour outages, a target rather than a guarantee (5 of 10). The API is v0, and Workflows and run search are labelled alpha or beta (5 of 10). - Performance: Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes. - Schema & documentation 84: A public OpenAPI 3 spec with 16 operations (25). llms.txt and Markdown copies of every page (10). Pages say when to use each primitive, and deprecated filters-mode endpoints name their replacement (16 of 20). Typed request bodies, with a query grammar fetched from a reference endpoint rather than enums (12 of 15). curl examples on every guide, but error bodies carry only a message with no stable codes (9 of 15). v0 in the path and a weekly product changelog that names CLI and MCP changes, without an API-specific log (12 of 15). - Agent ergonomics 66: Table queries select fields and take a limit, and searches return up to 500 per request (20 of 25). Cursor pagination and stateful iterators, structured filters and an advanced query language (20). Status codes as the error category and a message, with no stable codes in the API, though the CLI has typed exit codes (10 of 20). Items carry caller IDs for matching results and failed enrichments aren't charged, but there are no idempotency keys (8 of 20). No official SDKs, and the CLI is JSON-first (8 of 15). - Security & auth 48: A personal API key tied to the user's workspace access, with no scopes documented. The CLI uses OAuth per workspace (15 of 30). Functions need API or MCP access switched on one by one and workspace roles apply, but the Claude Code plugin's hook auto-approves most clay CLI commands, including ones that spend credits (8 of 20). Claygent web research returns untrusted text, and no injection guidance was found (3 of 15). Credit balances and a workflow-run query, with no per-call audit log found (6 of 15). Valid security.txt to July 2027, a trust centre, and SOC 2 Type II, ISO 27001 and ISO 42001 listed. No bug bounty found (16 of 20). - Payments & pricing 30: No x402, MPP or L402 (0). Data credits from $0.05 and plan prices public, though the plan cards and the FAQ disagree on the Launch and Growth prices (15 of 20). A free plan described as "no strings attached", with a card requirement not stated on the page (15 of 20). A person signs up in a browser, and CLI sign-in opens a browser or a device code (0). - Task success: Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored. - Maintenance & community 75: clay plugin 2.32.0 with CLI 1.9.0 on 6 October 2026 (30). Plugin releases on 25 September, 1, 2 (two) and 6 October (20). Weekly dated product roundups and a support address, with the plugin's issue handling not visible (12 of 15). No official SDKs, the CLI is current (8 of 15). CLI binaries ship from GitHub releases, and the repository has no licence file (5 of 10). - Transparency & trust 64: Closed service under terms dated 23 May 2024, and a plugin repository with no licence (12 of 30). The privacy policy dates from 11 September 2020, gives no retention periods and says nothing on AI training, and doesn't describe an opt-out for people whose data comes from Clay's providers (8 of 30). Deprecated endpoints are marked in the spec without removal dates (8 of 20). No sub-processor list found (0). Fix list for a coding agent, everything this grade says the listing lacks, the biggest gain first (12 items): https://www.anchorterminal.com/fixes/clay.md (JSON https://www.anchorterminal.com/fixes/clay.json) ### What we couldn't check - unchecked: status.clay.com components and incident history, which sat behind a bot check - unchecked: the Clay MCP endpoint, its authentication and tool list, which have no public reference - Whether the Public API is limited to Enterprise as the pricing FAQ says, or open to all plans as the developer docs imply - unchecked: trust.clay.com and privacy.clay.com, including any sub-processor list ### Sources - developer docs index: (seen 2026-10-14) - OpenAPI spec: (seen 2026-10-14) - authentication, errors and rate limits: (seen 2026-10-14) - search limits by plan: (seen 2026-10-14) - CLI basics: (seen 2026-10-14) - agent plugin repository: (seen 2026-10-14) - pricing: (seen 2026-10-14) - changelog: (seen 2026-10-14) - terms of service: (seen 2026-10-14) - privacy policy: (seen 2026-10-14) - security.txt: (seen 2026-10-14) - Clay MCP page: (seen 2026-10-14) ## Who's behind it (provenance 99/100, checked 2026-10-14) | Check | Finding | Points | | --- | --- | --- | | Legal entity named | Clay Labs Inc. | 20/20 | | Domain age | clay.com, registered 1992-11-13 (33 years) | 15/15 | | Endpoint on the vendor's domain | api.clay.com | 15/15 | | Terms of service | read, states 6 of the 7 things a reader expects | 9.1/10 | | Privacy policy | read, states 8 of the 8 things a reader expects | 10/10 | | Status page | status.clay.com | 10/10 | | Changelog | published | 10/10 | | security.txt | valid | 10/10 | The terms (last updated 23 May 2024) name Clay Labs Inc. with New York law. The privacy policy is dated 11 September 2020. clay.com/.well-known/security.txt names security@clay.com and trust.clay.com, expiring 2027-07-31. status.clay.com answered with a bot check to both curl and WebFetch, so its components and history weren't read. The API answers at api.clay.com and the docs at developers.clay.com. RDAP gives clay.com a registration date of 1992-11-13. ### Terms and privacy, as read A reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice. **Terms of service** (https://www.clay.com/terms-of-service), read 2026-10-14, dated 2024-05-23, states 6 of the 7 things a reader expects. - To know. Requires arbitration or waives class actions. "IMPORTANT NOTE: The section titled “Settling disputes between you and Clay” contains an arbitration clause and a class-action waiver." - Gives the date it was last updated. Last updated 2024-05-23. - Names the governing law or courts. Disputes go to the courts of New York, New York. - Not found in the text. Says how changes to the terms are announced. - Refers to a service level or uptime commitment. Names 99.0% availability. - Also in the text (2026-10-14). Paid contracts renew automatically at Clay's current rates when the subscription ends unless the customer cancels. "Your contract will automatically renew at Clay’s most-up-to-date-rates when your subscription ends." - Also in the text (2026-10-14). Customers may not resell any data they obtain from Clay. "You also agree not to re-sell any data you obtain from Clay." - Also in the text (2026-10-14). The customer releases Clay Labs from all claims of any kind related to or arising from use of the Services. "You hereby release and discharge Clay Labs, its officers, directors, employees, agents, and successors from any and all claims, demands, losses, damages, rights, and actions of any kind" **Privacy policy** (https://www.clay.com/privacy), read 2026-10-14, dated 2020-09-11, states 8 of the 8 things a reader expects. - To know. Has not been updated for three years or more. "Last updated September 11th, 2020" - Gives the date it was last updated. Last updated 2020-09-11. - Says how long data is kept. For as long as needed, with no period named. - Says whether personal data is sold or shared for advertising. Says it does not sell personal data. - Gives a privacy contact. team@clay.com. - Says where data is transferred or stored. Relies on standard contractual clauses. ## Live (updated 2026-10-14 09:41 UTC) - Right now: up, HTTP 401, 152 ms, checked 2026-10-14 09:41 UTC (get on `https://api.clay.com/public/v0`, asks for auth) - Uptime 24h 100.0% (17 probes) · 30 days 100.0% (17 probes) · p50 149 ms · p95 229 ms - Vendor status page: unknown, no machine-readable status found - Always current: https://www.anchorterminal.com/api/v1/live/clay.json ## Probe metrics Not measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score. ## Prices | Item | Price | Unit | Note | | --- | --- | --- | --- | | Data credit | $0.05 | per credit | Starting price per the pricing FAQ. Used when buying data from Clay's providers. Cheaper at volume | | Launch plan | $167 | per month (plan) | Plan card headline. The FAQ says from $185 a month | Across all listings: https://www.anchorterminal.com/prices/index.md ## Strengths - Public OpenAPI spec, llms.txt and Markdown copies of the docs - Search and enrichment across Clay's database and 150+ providers through one API - Failed enrichments use no credits or actions - CLI with JSON output and typed exit codes, released five times between 25 September and 6 October 2026 - Valid security.txt and SOC 2 Type II listed ## Weaknesses - API keys carry no scopes and act with the user's workspace access - The Claude Code plugin auto-approves most clay CLI commands, including ones that spend credits - No request-rate number published, and error bodies have no stable codes - Privacy policy dated September 2020 with no retention periods - Pricing page gives two different prices for Launch and Growth, and says API access is Enterprise ## Before you call it (notes for agents) 1. Fetch GET /search/query-mode/reference before writing a search query 2. Poll routine results until a terminal 200, since 202 means still running 3. Expect HTTP 402 when a plan's search cap is hit, and tell the user the reset date 4. Check GET /credits/balance before large batch runs 5. Ask the user before enabling the plugin's auto-approve hook in a shared workspace ## Connect First request: ```bash curl https://api.clay.com/public/v0/me \ -H "clay-api-key: $CLAY_PUBLIC_API_KEY" ``` Claude Code: ```bash Set up the Clay plugin by following the steps in https://github.com/clay-run/agent-plugins ``` Through letme (picks today, calling later): https://letme.dev/clay. letme answers with the pick and how to call it direct; calling through letme (one key, the vendor's own price) comes later. How it works: https://www.anchorterminal.com/letme/index.md ## Similar tools Ranked by shared capabilities, then score. Same-category tools with no shared capability key are listed last. | Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown | | --- | --- | --- | --- | --- | --- | --- | | Apollo API + MCP | B | 63.3 | 423 | lead.search, lead.enrichment, email.finder, data.company | no | https://www.anchorterminal.com/tools/apollo.md | | Coresignal API + MCP | B | 62.9 | 439 | lead.search, lead.enrichment, email.finder, data.company | no | https://www.anchorterminal.com/tools/coresignal.md | | Lusha API + MCP | B | 62.3 | 462 | lead.search, lead.enrichment, email.finder, data.company | no | https://www.anchorterminal.com/tools/lusha.md | | LeadMagic API + MCP | C | 60.2 | 555 | lead.search, lead.enrichment, email.finder, data.company | no | https://www.anchorterminal.com/tools/leadmagic.md | | FullEnrich API + MCP | C | 59.6 | 572 | lead.search, lead.enrichment, email.finder, data.company | no | https://www.anchorterminal.com/tools/fullenrich.md | | Hunter API + MCP | C | 56.5 | 670 | email.finder, lead.search, lead.enrichment, data.company | no | https://www.anchorterminal.com/tools/hunter.md | ## Panel reviews (0) Reviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): . Desk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md ## Notable - The Public API v0 has 16 operations in its OpenAPI spec, covering credits, routines (single and batch runs), query-mode and filters-mode searches, table queries and workflow-run search, with filters-mode marked deprecated (source: ) - Search results through the API are capped by plan, from 50 a request and 100 per 30 days on Free to 500 a request and 10,000,000 per 30 days on Enterprise, and exceeding a cap returns HTTP 402 (source: ) - 429 responses carry Retry-After and, when available, X-RateLimit headers, but no request-rate number is published (source: ) - The Claude Code plugin installs a PreToolUse hook that auto-approves most clay CLI commands so the agent stops asking, except login, logout, api-keys, webhooks and feedback (source: ) - The terms say the service strives for 99.0 per cent monthly uptime, with a 5 per cent fee credit for each six-hour period of full unavailability (source: ) - #8 of 19 in Best lead, contact and company data APIs for AI agents: https://www.anchorterminal.com/best/lead-data/index.md - All 171 leads comparisons: https://www.anchorterminal.com/compare/lead-data/index.md ## Compare - [Apollo API + MCP vs Clay](https://www.anchorterminal.com/compare/apollo-vs-clay.md): B 63.3 vs C 57.7 - [Clay vs Coresignal API + MCP](https://www.anchorterminal.com/compare/clay-vs-coresignal.md): C 57.7 vs B 62.9 - [Clay vs Crustdata API + MCP](https://www.anchorterminal.com/compare/clay-vs-crustdata.md): C 57.7 vs D 53.4 - [Clay vs Enrich Layer API + MCP](https://www.anchorterminal.com/compare/clay-vs-enrich-layer.md): C 57.7 vs C 55.8 - [Clay vs Explorium AgentSource](https://www.anchorterminal.com/compare/clay-vs-explorium-agentsource.md): C 57.7 vs D 48.1 - [Clay vs FullEnrich API + MCP](https://www.anchorterminal.com/compare/clay-vs-fullenrich.md): C 57.7 vs C 59.6 - [Clay vs Fuse MCP](https://www.anchorterminal.com/compare/clay-vs-fuse-mcp.md): C 57.7 vs D 47.9 - [Clay vs Gojiberry](https://www.anchorterminal.com/compare/clay-vs-gojiberry.md): C 57.7 vs D 47.9 - [Clay vs Hunter API + MCP](https://www.anchorterminal.com/compare/clay-vs-hunter.md): C 57.7 vs C 56.5 - [Clay vs LeadMagic API + MCP](https://www.anchorterminal.com/compare/clay-vs-leadmagic.md): C 57.7 vs C 60.2 - [Clay vs Lusha API + MCP](https://www.anchorterminal.com/compare/clay-vs-lusha.md): C 57.7 vs B 62.3 - [Clay vs People Data Labs](https://www.anchorterminal.com/compare/clay-vs-people-data-labs.md): C 57.7 vs B 64.2 - [Clay vs Prospeo API + MCP](https://www.anchorterminal.com/compare/clay-vs-prospeo.md): C 57.7 vs D 50.9 - [Clay vs RocketReach API](https://www.anchorterminal.com/compare/clay-vs-rocketreach.md): C 57.7 vs D 51.2 - [Clay vs ZoomInfo API + MCP](https://www.anchorterminal.com/compare/clay-vs-zoominfo.md): C 57.7 vs BB 72.2 - [Clay vs Clearbit](https://www.anchorterminal.com/compare/clay-vs-clearbit.md): C 57.7 vs F 13.5 - [Clay vs Dropcontact API + MCP](https://www.anchorterminal.com/compare/clay-vs-dropcontact.md): C 57.7 vs D 50.9 - [Clay vs FullContact](https://www.anchorterminal.com/compare/clay-vs-fullcontact.md): C 57.7 vs D 51.8 ## Verify this listing For the vendor. The badge or a plain link to this page verifies the listing, from a page on clay.com or one of its subdomains, or the README of github.com/clay-run/agent-plugins. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{"slug": "clay", "url": "…"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify HTML badge: ```html Clay on Anchor Terminal ``` Markdown badge, for a README: ```markdown [![Clay on Anchor Terminal](https://www.anchorterminal.com/badges/clay.svg)](https://www.anchorterminal.com/tools/clay) ``` Plain link: ```html Clay on Anchor Terminal ``` ## Share this listing For the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say Clay is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score. - Dark: https://www.anchorterminal.com/assets/share/clay-dark.png - Light: https://www.anchorterminal.com/assets/share/clay-light.png - Create a video and download its frames: https://www.anchorterminal.com/assets/listing-video/index.html?listing=clay