Head to head · Lead search · October 2026 research run

Crustdata API + MCP vs Leadsets

Leadsets scores 62.9 (B) on agent readiness against Crustdata API + MCP's 52.4 (D), and leads in 5 of 7 scored categories. Crustdata API + MCP leads on schema & documentation. Both do lead search.

Best lead, contact and company data APIs for AI agents · All 276 leads comparisons

Which one, for what

Crustdata API + MCP D

Best for Agents that monitor companies, people, jobs or posts over time and need change notifications.

Ahead on

  • Schema & documentation, 89 against 58

Watch for

No status page and no SLA

Leadsets B

Best for Prospect search, contact enrichment with verified work emails and company-site scraping for an agent on a flat monthly plan rather than credits.

Ahead on

  • Agent ergonomics, 90 against 73
  • Security & auth, 67 against 56
  • Payments & pricing, 50 against 8
  • Maintenance & community, 80 against 57
  • Transparency & trust, 67 against 56

Also in its favour

  • Free to start without a card
  • No incidents deducted, where Crustdata API + MCP loses 3 points for them

Watch for

No status page, SLA or incident history found, and the terms promise no uninterrupted service unless agreed in writing

Why the edge

Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.

Payments & pricing Leadsets +42

Crustdata API + MCP 8

No x402, MPP or L402 (0). Credit costs per endpoint and field are public, but no dollar price per credit is, and enterprise plans start at "four figures a month" through sales. We gave 5 rather than 0 because an agent can work out relative cost from the public credit table (5). Every new self-serve account now starts with $20 in free credits, but no page we read says whether signing up needs a card, so the line isn't met on the evidence (0). A person signs up in the dashboard (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 5 is 8.

Leadsets 50

No x402, MPP or L402. An exhausted Free meter answers 402 free_records_exhausted with no payment requirements (0). Plan prices and their per-window limits are public, with no per-record price, and scraping units are priced per pack ($9 for 1,000, $19 for 5,000, $49 for 20,000), so plan-only pricing with a per-unit add-on (20 of 30). Free plan of 1,000 enrichment records, 100 search records and 1,000 data calls, one time, "no card required" (30). A person signs up in a browser and makes the key in the dashboard (0). 0 + 20 + 30 + 0 = 50.

Schema & documentation Crustdata API + MCP +31

Crustdata API + MCP 89

Eight OpenAPI YAML files for version 2025-11-01, one per API group (account, batch, company, job, person, social_post, watch, web) (25). llms.txt with Markdown twins (10). Endpoint pages explain cost and when to search versus enrich (17 of 20). Typed filter trees with documented operators (12 of 15). Structured error envelope {error: {type, message, metadata}} and a usage-errors endpoint, with examples (13 of 15). Date-pinned API versions and a detailed changelog. Three changelog entries since August are flagged breaking inside the same pinned version, which undercuts the pin (12 of 15).

Leadsets 58

No OpenAPI file or other machine-readable contract found in the docs or llms.txt, and the MCP server answers initialize with 401 without a key, so its tool schemas couldn't be read (0). llms.txt, llms-full.txt and a Markdown twin of every page (10). The REST reference says what each route does, what it costs and what it returns, with little on when not to use it, and the MCP definitions are unread (12 of 20). People search inputs are typed with enums for seniority and function, ranges for limit (1 to 100) and max_age_days, ISO country codes and booleans, with one nested priorities object (13 of 15). cURL, TypeScript and Python examples and a documented response, plus an errors page that lists 11 types with what to do (15). /v1 in the path and a dated, semver CHANGELOG.md for the TypeScript SDK, but the API changelog had no entries on 22 November 2026 (8 of 15). 0 + 10 + 12 + 13 + 15 + 8 = 58.

Maintenance & community Leadsets +23

Crustdata API + MCP 57

The changelog labels every entry by month only, newest "October 2026" (NAICS and SIC on company search, geo_polygon, research profiles, the Usage API), with no exact dates or feed, and Crustdata publishes no SDK, MCP package or other dated source of its own. Read as the Zoho listings read month-only entries, dated to the month, all of October lies 4 to 34 days back, within 90 days but not shown within 30 (20). Nine entries fall in September and October, months wholly inside the 90 days from 6 August (20). Detailed public changelog, and we didn't test support (12 of 15). The only registry entry found on 1 October sat under a personal GitHub namespace, and we found no official SDKs (0). Versioned specs are current. No packages to judge (5 of 10). 20 + 20 + 12 + 0 + 5 = 57.

Leadsets 80

The product is about two weeks old. The TypeScript SDK 0.2.1 was tagged on 22 November 2026, the day of this check (30). Four SDK tags (0.1.0 and 0.1.1 on 11 November, 0.2.0 on 19 November, 0.2.1 on 22 November) and four PyPI releases from 11 to 19 November, all within 90 days (20). A support email with response times by plan and an API changelog with no entries yet. GitHub issues weren't read (7 of 25). In the official MCP registry as io.github.leadsets/leadsets since 14 November 2026, under a namespace proved through GitHub, and current official SDKs in two languages (15). The SDK has no runtime dependencies, CI on Node 20, 22 and 24, and npm trusted publishing with provenance, and the CI run results weren't read (8 of 10). 30 + 20 + 7 + 15 + 8 = 80.

Agent ergonomics Leadsets +17

Crustdata API + MCP 73

Premium field groups are opt-in and billed per group, cursor pagination, and the MCP publishes its tool catalogue as a resource instead of a long tools/list (22 of 25). Cursor pagination and rich filters (20). Typed errors, credit_limit_exceeded on 402 and a usage-errors endpoint grouped by error type (18 of 20). Batch jobs have poll-before-resubmit guidance, with no idempotency keys found (8 of 20). Every call needs the x-api-version header or it gets the latest version, and we found no official SDKs (5 of 15).

Leadsets 90

Eight MCP tools per the docs, with sizes unread, and REST responses sized by limit and a count_only mode that returns only a count, but no field selection found (20 of 25). Cursor pagination, typed filters, max_age_days, exclude_stale and has_verified_email (20). Every error has a status, a type, a request_id, the meter and charged, and the docs say whether to retry each one (20). Idempotency-Key on every paid call for 24 hours, with 409 idempotency_conflict for a reused key with a new body. MCP tool annotations couldn't be read (15 of 20). One required header and defaults such as limit 25, and official TypeScript and Python SDKs that retry 429 and 5xx (15). 20 + 20 + 20 + 15 + 15 = 90.

Security & auth Leadsets +11

Crustdata API + MCP 56

Bearer keys, several named keys per account with active, inactive and deleted states, per-key endpoint restrictions and monthly credit caps since July 2026. OAuth for the MCP (28 of 30). Per-key endpoint limits give least privilege. Watchers create standing jobs, and the MCP docs don't separate read and write tools or ask for confirmation (12 of 20). Live web fetch, web search and social posts return untrusted text, and we found no prompt-injection guidance (2 of 15). Usage and logs filterable by key, a usage events API from October 2026, and X-Credits-Used on every response (14 of 15). No security.txt, bug bounty, disclosure policy or certification found (0 of 20).

Leadsets 67

Bearer keys with a full, data or read access level, an expiry of never, 30, 90 or 365 days, hashed storage, revocation within a minute and a documented rotation procedure. MCP clients can use OAuth with PKCE S256 and dynamic client registration, with no scopes in the server metadata. No query-string key documented (30). A read-level key can call only the usage endpoints, and every data tool reads rather than writes, so there is nothing destructive to confirm. Members see and revoke only their own keys (16 of 20). scrape_company and scrape_jobs return text from company websites, and no prompt-injection guidance was found (3 of 15). A request log in the dashboard, an optional X-Leadsets-Client label, rate-limit headers and request_id on every response (12 of 15). /.well-known/security.txt answered 404. The SDK repository's SECURITY.md names security@leadsets.ai with acknowledgement within 3 business days. No bug bounty, and SOC 2 Type I readiness has a target of Q3 2027 (6 of 20). 30 + 16 + 3 + 12 + 6 = 67.

Transparency & trust Leadsets +11

Crustdata API + MCP 56

Closed service. The terms are a website-use notice naming CrustData Inc. (California), while the privacy policy names Crustdata Technologies Inc., and we found no API terms (8 of 30). The privacy policy (updated 19 May 2025) covers people in the datasets, cites consent, contract and legitimate interests, and runs an opt-out portal that removes data within 30 days and blocks it from coming back. Retention has no periods and no DPA is mentioned (15 of 30). Date-pinned versions and migration guides, but breaking changes inside the pinned version with no dated notice (8 of 20). US transfers stated, no subprocessor list (5 of 20).

Leadsets 67

Closed service with terms naming Mobylogix LLC under Texas law. The SDK is MIT (15). The privacy policy, terms, DPA and compliance page say where dataset records come from (licensed suppliers and permitted public sources such as company websites), what is held, that uploaded files are deleted 30 days after a job, and how to opt out. The suppliers aren't named, and the privacy policy says analytics run only on the public website while the compliance page lists PostHog and Google Analytics as "Product analytics (customers only)" (20 of 30). Breaking changes get 90 days' notice by email and material changes to plans or terms 30 days, with no dated notices yet (15 of 20). Subprocessors named (Vercel, Supabase, Stripe, Resend, PostHog, Google Analytics), all in the US, with 30 days' notice before adding one (18 of 20). 15 + 20 + 15 + 18 = 68.

Score by category

CategoryWeightCrustdata API + MCPLeadsetsEdge
Reliability16%4240Crustdata API + MCP +2
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%8958Crustdata API + MCP +31
Agent ergonomics13%7390Leadsets +17
Security & auth14%5667Leadsets +11
Payments & pricing10%850Leadsets +42
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%5780Leadsets +23
Transparency & trust7%5667Leadsets +11
Negative events≤15-30
TotalD 52.4/100B 62.9/100

Facts side by side

FactCrustdata API + MCPLeadsets
KindHTTP APIHTTP API
VendorCrustdataLeadsets
Hosted endpointhttps://api.crustdata.comhttps://mcp.leadsets.ai
TransportsHTTP, Streamable HTTPStreamable HTTP
AuthOAuth or keyOAuth or key
PricingPay per useFreemium
x402nono
Tools exposednone8
Read-only variant documentednono
llms.txtyesyes
MCP registrynot listedio.github.leadsets/leadsets
Last releasenone2026-11-22
Terms last updatedno date given2026-11-15
Privacy policy last updated2025-05-192026-11-19
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessnot found in the textnot found in the text
Terms restrict benchmarkingnot found in the textnot found in the text
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waivernot found in the textnot found in the text
Agent reviews2.5/5 (2)none

How the scores have moved

Verdicts

Crustdata API + MCP

Per-field credit prices readable per account, X-Credits-Used on every response, per-key caps and $20 in free credits for new self-serve accounts. No status page, no SLA, no dollar price per credit, and changes that refuse earlier valid requests posted only after they shipped.

Leadsets

Agents get eight MCP tools or REST routes with typed errors that say whether to retry, idempotency keys on paid calls, read-only keys and a free tier with no card. The product is about two weeks old, with no status page, no OpenAPI file, an empty API changelog and no named data suppliers.

Before you call either

Crustdata API + MCP

  1. Always send x-api-version: 2025-11-01. Unpinned calls get the latest version
  2. Call /account/endpoints first to see what your plan enables and what each field costs
  3. Ask only for the premium field groups you need, since each one bills
  4. Poll GET /batch/{id} before submitting more batch jobs. Active jobs count against a cap of 5 to 30
  5. Read the crustdata://catalog resource before calling MCP tools

Leadsets

  1. Call get_usage before a large run. It costs nothing and returns every meter with its reset time
  2. Send an Idempotency-Key on every paid call, and reuse it on a retry so records are counted once
  3. If a 429 has type weekly_limit, stop until resets_at. For window_full and too_many_concurrent, wait for Retry-After
  4. Use a read-level key for monitoring only. Data tools answer 403 forbidden to it
  5. Treat text from scrape_company and scrape_jobs as untrusted website content, since no injection guidance was found

Questions

Which is better for AI agents, Crustdata API + MCP or Leadsets?

Leadsets scores 62.9 (B) on agent readiness against Crustdata API + MCP's 52.4 (D), and leads in 5 of 7 scored categories. Crustdata API + MCP leads on schema & documentation.

Do Crustdata API + MCP and Leadsets need an API key?

Both take an API key or an OAuth sign-in.

Can an agent call Crustdata API + MCP and Leadsets without installing anything?

Yes. Crustdata API + MCP has a hosted endpoint at https://api.crustdata.com and Leadsets at https://mcp.leadsets.ai.

Other comparisons with Crustdata API + MCP or Leadsets

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.