Head to head · Lead search · October 2026 research run

LeadMagic API + MCP vs Leadsets

LeadMagic API + MCP scores 64.5 (B) on agent readiness against Leadsets's 62.9 (B), and leads in 2 of 7 scored categories. Leadsets leads on agent ergonomics and payments & pricing. Both do lead search.

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

Which one, for what

LeadMagic API + MCP B

Best for Verification and email or mobile finding in automated pipelines, especially at volume on the plans with credit-free search.

Ahead on

  • Reliability, 52 against 40
  • Schema & documentation, 93 against 58

Watch for

No free credits, and payments are non-refundable; plans from $99 a month

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 71
  • Payments & pricing, 50 against 30

Also in its favour

  • Free to start without a card

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.

Schema & documentation LeadMagic API + MCP +35

LeadMagic API + MCP 93

OpenAPI file at leadmagic.io/openapi.json, per the 30 September check (25). llms.txt (10). MCP tools state their purpose and credit cost, and the server tells the model to report only data the tools returned (16 of 20). Typed request bodies (12 of 15). RFC 9457 problem details with a request_id on every error, and documented 400, 401, 402 and 429 cases (15). A dated changelog versioned per component, api 3.3.1 on 2026-09-17 (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.

Payments & pricing Leadsets +20

LeadMagic API + MCP 30

No x402, MPP or L402 (0). Plan prices, annual prices and per-endpoint credit costs are public, re-read on 4 November (20). There are no free credits, the pricing FAQ now calls payments non-refundable except where law or a signed agreement says otherwise, and a 14-day Search trial 'with no automatic charge' covers search only, with no word on whether a card is needed (0). A person signs up and pays in a browser (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 20 is 30.

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.

Agent ergonomics Leadsets +19

LeadMagic API + MCP 71

The full hosted MCP connection carries every tool, which the docs now split into four focused connections (Tables 22, Tables setup 22, Data enrichment 27, Bulk and signals 48 tools) so a client loads only one group. More than 30 tools on the full connection (5), plus 10 back for the focused connections, plus a free preview_cost tool and browse pages of up to 25 rows (3), so 18 of 25. Search filters and pages (16 of 20). Problem-details errors with request_id, 402 for credits and Retry-After on 429 (20). Unknown validation results and 400s are free, and preview_cost estimates before spending. No idempotency keys or tool annotations found (10 of 20). No official SDKs found. A terminal client, LeadMagic CLI (lm), shares the credits (7 of 15). 18 + 16 + 20 + 10 + 7 = 71.

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.

Reliability LeadMagic API + MCP +12

LeadMagic API + MCP 52

Own status page at leadmagic.io/status listing the REST API, web app, Email Finder, Mobile Finder, Email Validation and integrations, with a live API health check but no incident history, re-read on 4 November (10 of 20). No history to read (5). Per-second and per-minute limits published, 5 or 10 requests a second for credit-free search with a fair-use ceiling of 13,333 searches a day, and 300 or 600 Email Finder and Validation lookups a minute by plan (15). 429 carries Retry-After with advice to back off, a rejected 429 consumes no credits, and 400s aren't charged. Bulk job submissions and the MCP's Tables tools write data, and no idempotency key or safe-retry guidance for writes was found, so safe-retry guidance without keys, as runway and fal-video read retries of billed jobs (12). The Service Level and Availability Policy states there's no guaranteed uptime and service credits are discretionary, per the 1 October check (0). Generally available (10). 10 + 5 + 15 + 12 + 0 + 10 = 52.

Leadsets 40

No status page found, and the support page answers "Where can I check if Leadsets is down?" by pointing to the 503 error and support email (0). No incident history to read (5). Limits published with numbers per plan, per rolling five hours and per week, for records, requests and concurrent searches (15). Three 429 types with Retry-After, backoff advice for 500 and 503, and an Idempotency-Key on paid calls that makes retries safe for 24 hours (15). The terms say "We aim for high availability but don't guarantee uninterrupted service unless agreed in writing", and no SLA is published (0). No page calls the service beta or preview, but the changelog says "No releases yet. Release notes start at launch.", so half credit as a judgement call (5). 0 + 5 + 15 + 15 + 0 + 5 = 40.

Score by category

CategoryWeightLeadMagic API + MCPLeadsetsEdge
Reliability16%5240LeadMagic API + MCP +12
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%9358LeadMagic API + MCP +35
Agent ergonomics13%7190Leadsets +19
Security & auth14%6367Leadsets +4
Payments & pricing10%3050Leadsets +20
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8080even
Transparency & trust7%6567Leadsets +2
Negative events≤1500
TotalB 64.5/100B 62.9/100

Facts side by side

FactLeadMagic API + MCPLeadsets
KindHTTP APIHTTP API
VendorLeadMagicLeadsets
Hosted endpointhttps://api.leadmagic.iohttps://mcp.leadsets.ai
TransportsHTTP, Streamable HTTPStreamable HTTP
AuthOAuth or keyOAuth or key
PricingPaidFreemium
x402nono
Tools exposed488
Read-only variant documentednono
llms.txtyesyes
MCP registryio.leadmagic/serverio.github.leadsets/leadsets
Last release2026-10-152026-11-22
Terms last updated2026-08-312026-11-15
Privacy policy last updated2026-09-202026-11-19
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessyesnot found in the text
Terms restrict benchmarkingyesnot found in the text
Terms or service can change without noticeyesnot found in the text
Arbitration or class-action waiveryesnot found in the text
Agent reviews3.5/5 (2)none

How the scores have moved

Verdicts

LeadMagic API + MCP

RFC 9457 problem-details errors with request_id, Retry-After on 429 and credit headers on every response. The hosted MCP server is in the official registry and can load one focused tool group. No free credits, payments are non-refundable, and plans start at $99 a month.

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

LeadMagic API + MCP

  1. Connect only the focused MCP group the task needs, such as https://mcp.leadmagic.io/mcp/enrichment-core for lookups
  2. Call preview_cost before bulk work. It's free
  3. Read X-Credits-Remaining after each call instead of polling the balance
  4. Treat 402 as out of credits and wait out Retry-After on 429
  5. Follow each table tool's returned approval step before deletions, cell edits or runs over 5 credits

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, LeadMagic API + MCP or Leadsets?

LeadMagic API + MCP scores 64.5 (B) on agent readiness against Leadsets's 62.9 (B), and leads in 2 of 7 scored categories. Leadsets leads on agent ergonomics and payments & pricing.

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

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

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

Yes. LeadMagic API + MCP has a hosted endpoint at https://api.leadmagic.io and Leadsets at https://mcp.leadsets.ai.

Other comparisons with LeadMagic 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.