Head to head · Lead search · October 2026 research run

Gojiberry vs Leadsets

Leadsets scores 62.9 (B) on agent readiness against Gojiberry's 48.9 (D), and leads in 5 of 7 scored categories. Gojiberry leads on reliability and schema & documentation. Both do lead search.

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

Which one, for what

Gojiberry D

Best for A founder or small sales team that wants an agent to pull scored, signal-based B2B leads and run LinkedIn and email outreach from one paid workspace.

Ahead on

  • Reliability, 70 against 40
  • Schema & documentation, 71 against 58

Watch for

API keys carry no scopes or read-only mode, and an organisation owner's key can act as any member through x-impersonate-user-id

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 55
  • Security & auth, 67 against 31
  • Payments & pricing, 50 against 15
  • Maintenance & community, 80 against 20
  • Transparency & trust, 67 against 61

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.

Maintenance & community Leadsets +60

Gojiberry 20

No changelog or dated API release was found. The developer docs carry no dates, and their sitemap stamps record no change. The newest dated evidence is help-centre editing. The MCP article is dated 29 September 2026 and the API article 21 August 2026, so the partial credit for activity inside 90 days is kept (15 of 30). No dated releases to count (0). Live chat and hello@gojiberry.ai for support, not tested, and no public changelog (5 of 15). No readable registry page names the server and no official SDKs exist (0). Package health 5 to 0, an in-between value with no package behind it. 15 + 0 + 5 + 0 + 0 = 20.

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.

Security & auth Leadsets +36

Gojiberry 31

Credential line 18 to 20. Bearer API keys created in the app and shown once, now with a documented way to revoke them (deleting a key in Settings, API cuts its access at once). No scopes, and an organisation owner's key can act as any member through x-impersonate-user-id. The MCP server signs users in with OAuth and creates a key named after the client app (20 of 30). No read-only mode on the API. The MCP page says tools that change data are flagged so clients can ask first, and warns that send_unibox_message and the deletes can't be undone, but the server enforces nothing (3 of 20). Results carry LinkedIn profile text and inbound messages, with no prompt-injection guidance found (2 of 15). Campaign and agent logs and team activity through the API, a credit usage history in the app, no per-key call log found (6 of 15). No security.txt (404 on 4 November), disclosure policy, bounty or certification found. The privacy policy states encryption in transit and at rest, which is none of the programme line's items, so the line is 0 (was 3, a value with no programme evidence behind it). 20 + 3 + 2 + 6 + 0 = 31.

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.

Agent ergonomics Leadsets +35

Gojiberry 55

On the API, search returns masked rows until revealed, but a Contact has 75 fields and no field selection (14 of 25). page and limit on lists, eleven filters on contacts and fifteen on lead search (17 of 20). Status codes are documented per operation, with 402 for credits, 409 and 422. Bodies are {message, statusCode} and there's no error catalogue (11 of 20). No idempotency keys. Search is deterministic, a deleted contact can't be created again, and failed enrichments cost nothing. The MCP page says tools that change data are flagged, which we couldn't read from the server (7 of 20). Few required parameters and stated defaults, no official SDKs (6 of 15). 14 + 17 + 11 + 7 + 6 = 55.

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.

Payments & pricing Leadsets +35

Gojiberry 15

No x402, MPP or L402 (0). The Pro plan is public at $99 a month, and credit costs per action are published, but no dollar price per credit was found (10). There's a free trial, and the help centre says the subscription then starts on the saved payment method, so we read it as needing a card. We didn't open the signup form (0). A person signs up in a browser and the terms forbid account creation by bots (0). 0 + 10 + 0 + 0 = 10. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 10 is 15.

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.

Reliability Gojiberry +30

Gojiberry 70

Graded with the hosted lines. Status page at status.gojiberry.ai on Better Stack with two components, gojiberry.ai and api.gojiberry.ai, and 90-day bars. Neither names ext.gojiberry.ai or mcp.gojiberry.ai, the hosts an agent calls, so the page has no component for the product (15, was 20). Both show 100 per cent, and the incident history lists none for September, October or November 2026 (August per the 8 October check). The page has not been shown to post any incident, so 20 rather than a clean record (was 22, an in-between value; tldv, zamp). The quickstart and the OpenAPI file state 100 requests a minute and 100,000 a day per account, shared by all keys and MCP connections, with lower limits on some endpoints (15). 429 line 7 to 10. Requests over a limit now get 429 Too Many Requests with a Retry-After header and the instruction to wait that long before retrying. No idempotency keys or safe-retry guidance for writes, so Retry-After alone (10). No SLA found, and the terms say the service is supplied as is (0). API version 1.0 with no beta label (10). 15 + 20 + 15 + 10 + 0 + 10 = 70.

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.

Schema & documentation Gojiberry +13

Gojiberry 71

Gojiberry moved its developer docs to dev.gojiberry.ai (Mintlify), and ext.gojiberry.ai/documentation now redirects there. Public OpenAPI 3.0.0 file, version 1.0, with 56 operations on 45 paths, linked from the docs' llms.txt under OpenAPI Specs (25). llms.txt 0 to 10. dev.gojiberry.ai serves llms.txt and every page as Markdown. 47 of 56 operations carry a description, and many say when to use them, such as the async enrichment routes for MCP clients and free search before paid reveal (15 of 20). 25 enums, 23 required lists and 50 required parameters, but search results are untyped objects and only four length bounds appear (9 of 15). 73 examples and curl samples. Error responses are a status code and a sentence, none of the 53 error responses has a body schema (8 of 15). A /v1 path and version 1.0, with no changelog found (4 of 15). 25 + 10 + 15 + 9 + 8 + 4 = 71.

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.

Score by category

CategoryWeightGojiberryLeadsetsEdge
Reliability16%7040Gojiberry +30
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%7158Gojiberry +13
Agent ergonomics13%5590Leadsets +35
Security & auth14%3167Leadsets +36
Payments & pricing10%1550Leadsets +35
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%2080Leadsets +60
Transparency & trust7%6167Leadsets +6
Negative events≤1500
TotalD 48.9/100B 62.9/100

Facts side by side

FactGojiberryLeadsets
KindHTTP APIHTTP API
VendorSUPERFRUITS SAS (Gojiberry AI)Leadsets
Hosted endpointhttps://ext.gojiberry.aihttps://mcp.leadsets.ai
TransportsHTTP, Streamable HTTPStreamable HTTP
AuthOAuth or keyOAuth or key
PricingPaidFreemium
x402nono
LicenceProprietary service under Gojiberry's General Termsnone
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 updatedno date given2026-11-19
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessyesnot found in the text
Terms restrict benchmarkingnot found in the textnot found in the text
Terms or service can change without noticeyesnot found in the text
Arbitration or class-action waivernot found in the textnot found in the text

How the scores have moved

Verdicts

Gojiberry

A public OpenAPI file with 56 operations linked from the developer docs' llms.txt, a free masked lead search and published limits of 100 requests a minute with Retry-After make the API easy to plan against. Keys have no scopes, an owner's key can act as any member, and writes can start LinkedIn and email outreach from connected accounts.

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

Gojiberry

  1. Connect MCP clients to https://mcp.gojiberry.ai/mcp and sign in to Gojiberry. Custom clients must send a User-Agent header or get a 403
  2. Create resources in the order list, source agent, campaign. A source agent with no campaign only finds leads
  3. Adding a contact to a list enrols it in the linked campaign, which sends LinkedIn or email messages. Ask the user before list writes
  4. Search with POST /v1/directory/leads/search for free, then reveal only the ids you need at 0.5 credit each
  5. On a 429, wait for the Retry-After seconds before retrying. Limits are shared by every key and MCP connection of the account

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, Gojiberry or Leadsets?

Leadsets scores 62.9 (B) on agent readiness against Gojiberry's 48.9 (D), and leads in 5 of 7 scored categories. Gojiberry leads on reliability and schema & documentation.

Do Gojiberry and Leadsets need an API key?

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

Can an agent call Gojiberry and Leadsets without installing anything?

Yes. Gojiberry has a hosted endpoint at https://ext.gojiberry.ai and Leadsets at https://mcp.leadsets.ai.

Other comparisons with Gojiberry 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.