Head to head · Market fundamentals · October 2026 research run

Financial Datasets vs TickerLayer

TickerLayer scores 71.5 (BB) on agent readiness against Financial Datasets's 61.8 (C), and leads in 5 of 7 scored categories. Financial Datasets leads on transparency & trust. Both do market fundamentals.

Best financial market data APIs for AI agents · All 78 markets comparisons

Which one, for what

Financial Datasets C

Best for An agent doing US company research from SEC-sourced statements, filings, insider and institutional data that wants to pay per call with no account, or a small team on credits.

Ahead on

  • Transparency & trust, 63 against 38

Watch for

No status page, incident history or published uptime; the Professional plan's SLA terms aren't public

TickerLayer BB

Best for An agent that needs latest prices, bars and market hours across stocks, forex, crypto, indices, ETFs, commodities, bond yields and perpetual futures from one schema, and wants to pay per call without an account.

Ahead on

  • Reliability, 70 against 43
  • Schema & documentation, 88 against 80
  • Agent ergonomics, 79 against 73
  • Payments & pricing, 92 against 75
  • Maintenance & community, 79 against 56

Also in its favour

  • Agent-ready, a grade of BB or better
  • Free to start without a card

Watch for

The data is derived and indicative from unnamed non-exchange sources, and no page says it is licensed from an exchange

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.

Reliability TickerLayer +27

Financial Datasets 43

Graded as a hosted service. No status page was found; status.financialdatasets.ai does not resolve and no page links one (0), so there is no incident history to read (5). The only published limit is 10,000 requests a minute per wallet over x402, with monthly request caps per plan and none per minute for keyed plans (8 of 15). The OpenAPI file declares 429 and the x402 page documents a 503 with Retry-After from the facilitator and a duplicate_payment check on replayed signatures (10 of 15). The Professional plan lists uptime SLAs, with no figure published (10). The API is generally available (10). Total 43.

TickerLayer 70

Read with the hosted lines, on the REST API. status.tickerlayer.com is an UptimeRobot page linked from the site header (20). Its monitors and history load by script from /api/, which its robots.txt disallows, so no incident record was read, as for eodhd and apitemplate-io (5). Limits are published with numbers, 10 requests a second per account on Free and Individual, 100 on Business, and monthly call quotas per feed (15). The OpenAPI file's 429 carries Retry-After and a body with retryAfterMs, resetsAt and a code that separates the per-second limit from the monthly quota, and every response has carried X-RateLimit-Limit and X-RateLimit-Remaining since 14 September 2026. Every data operation is a GET, and x402 retries with the same payment identifier return the stored response (15). An SLA is named only for Enterprise under a written agreement and as 'partially available' on Business, with no published terms or figure, and the terms of use promise no uptime. Financial-datasets took 10 for SLAs listed on a self-serve plan, so this is half (5 of 10). No beta or preview label on the REST API, the MCP server or the x402 gateway (10). 20+5+15+15+5+10 = 70.

Transparency & trust Financial Datasets +25

Financial Datasets 63

A closed service under terms dated 29 October 2026 that name Financial Datasets, Inc., set New York law, and state the licence per plan (15 of 30). The privacy policy of 20 August 2026 gives retention periods (accounts up to seven years after closure, API and MCP logs up to three years, backups 90 days), says inputs aren't used for training, and links a subprocessor list; no DPA text was found (24 of 30). No deprecation policy; the terms say the Services may be discontinued and material changes get reasonable notice (3 of 20). Subprocessors (AWS, Heroku, Stripe, Google sign-in, Vercel) and the United States as hosting location are disclosed (18 of 20). Total 60.

TickerLayer 38

The editorial half. A closed service whose terms of use, user agreement and market data disclaimer (all effective 3 November 2026) set out internal, commercial and redistribution rights by plan and a liability cap. They name no legal entity, address or governing law, so the contracting party is unknown. The plugin and npm client are MIT. Soldfetch took 10 in the same position (10 of 30). The privacy policy keeps WebSocket connection records for 7 days but gives no period for request and tool-call logs or account data after closure, says nothing on model training, names no transfer mechanism and has no DPA (12 of 30). No deprecation policy. The terms allow MCP tools to change 'with reasonable notice where practical' and the user agreement promises notice before a plan is materially reduced, and the changelog records changes after the fact. Kite took 4 (4 of 20). Subprocessors are given only as categories (hosting, authentication, card and crypto payments, email, an AI model for support replies), with analytics vendors deferred to the cookie policy, no data locations, and no named data suppliers (4 of 20). 10+12+4+4 = 30. The provenance half is computed from the provenance block.

Maintenance & community TickerLayer +23

Financial Datasets 56

UK fundamentals went live on 26 October 2026, India on 23 October, with Japan and South Korea dated for November on the coverage page (30). Dated changes in the last 90 days are x402 on 23 October, UK fundamentals on 26 October, terms and subprocessor list on 29 October, privacy policy on 20 August, with no changelog as such (12 of 20). Contact is a form and the dashboard; no support email, Discord or forum was found, and the GitHub organisation's four repositories couldn't be read because the GitHub API rate limit was reached (6 of 15). The PyPI package is 0.1.18 of 26 May 2024 by the founder, and the docs point to the OpenAPI file and the MCP server rather than an SDK (5 of 15). Package health unknown, dependencies not checked (3 of 10). Total 56.

TickerLayer 79

Read as a closed service. The newest changelog entry is 6 November 2026, a bond yield curve endpoint (30). 50 dated changelog entries from 8 September to 6 November 2026 (20). A public changelog, a consultation form, info@tickerlayer.com and a support chat, all untested, with no community channel and no issues on the plugin repository read. Massive and twelve-data took 10 (9 of 15). Official clients for JavaScript or TypeScript (npm) and Python (PyPI), both 0.1.0 from 20 October 2026, and an MCP registry entry under the verified namespace com.tickerlayer (15). The npm package has no dependencies or install hooks but no repository field, the clients' source isn't public and no CI is visible (5 of 10). 30+20+9+15+5 = 79.

Payments & pricing TickerLayer +17

Financial Datasets 75

x402 on the vendor's own endpoints for every documented GET data endpoint, 36 of them, with the last 365 days only and a Non-Professional licence; full history, the market snapshot, filing items and the POST endpoints need a key (35 of 40). Plan prices and overage rates are public, and each x402 endpoint quotes its price in the 402 header, $0.02 on /earnings (20). No free tier or trial found; data calls return 402 until an account holds credits, from $20 (0). An agent can pay by x402 with no account, or open an account with POST /agent/signup and have the owner fund it (20). Total 75.

TickerLayer 92

x402 on the vendor's own gateway, x402.tickerlayer.com, for 41 GET routes. That is six routes for each of stocks, forex, crypto, indices, ETFs and commodities, plus bond yields and four market-calendar routes. Perpetuals, Futures CFDs, the add-ons, the symbol catalogue and WebSocket need a key. Between massive's 30 for US stock routes only and financial-datasets' 35 for every documented data endpoint (32 of 40). Per-call x402 prices from 0.01 to 0.10 USDC in the catalogue and docs, and plan prices per feed on the pricing page, all without a login (20). A Free plan of 3,000 REST calls every 30 days with 'no card', per llms.txt (20). An agent with a funded Base wallet pays per call with no account or key (20). 32+20+20+20 = 92.

Schema & documentation TickerLayer +8

Financial Datasets 80

OpenAPI 3.0.1 at financialdatasets.ai/openapi.json, 68 operations with 13 response codes and one security scheme, named the source of truth by the docs (25). llms.txt and a Markdown twin of every page (10). Every operation has a description, and the 402 terms carry a resource description that says when an agent should use the endpoint (17 of 20). 330 parameters, 36 with enums, 32 required, no free-form blobs (12 of 15). Code samples in Python, JavaScript and curl, x402 error values documented, but response examples on only six operations in the spec (11 of 15). No API version and no changelog; the news page has four dated posts in 2026 (5 of 15). Total 80.

TickerLayer 88

OpenAPI 3.1 at tickerlayer.com/openapi.json (TickerLayer Market Data API 1.0.0, about 386,000 characters), read in its first 100,000 and last 96,000 characters, with summaries, descriptions, tags and examples on the operations read and shared 400, 401, 403, 404, 429 and 503 responses. The WebSocket is described in prose only and the hosted MCP tool schemas weren't read (23 of 25). llms.txt, llms-full.txt and a Markdown twin of every docs page (10). Operation descriptions state purpose and plan gating, and the vendor's skill says which MCP tool to use for each question and when not to, such as get_quote not being the tool for a price. Financial-datasets took 17 (17 of 20). Enums on interval, multiplier, timespan and sort, format: date on dates, bounded limit, required path parameters, as for massive (13 of 15). Examples on most parameters and responses, one Error schema with ten fields and documented codes, but the codes appear only as example values with no enum or table (13 of 15). A dated changelog of the last 50 changes, 8 September to 6 November 2026, but no version in the REST paths ('no /v1/') and the spec at 1.0.0. Above twelve-data's 10 for monthly updates and below massive's 15 for versioned paths (12 of 15). 23+10+17+13+13+12 = 88.

Agent ergonomics TickerLayer +6

Financial Datasets 73

limit and period on the data endpoints, as_reported flags and snapshot variants, with no field selection (15 of 25). next_page_url cursors and ticker, CIK, market and date filters (18 of 20). A 402 body says what to do next, x402 errors carry named values, and the spec lists 400, 401, 403, 404, 409, 422, 429, 502 and 503 (16 of 20). Data calls are GETs, payment settles only after a successful response, and a replayed x402 signature is refused; no readOnlyHint found for the MCP tools and no idempotency key for the POST endpoints (14 of 20). Few required parameters, 28 compact MCP tools, but the only package, financial-datasets on PyPI, is at 0.1.18 from 26 May 2024 (10 of 15). Total 73.

TickerLayer 79

Read on the REST API, with the MCP server where a line covers it. Responses are sized by limit (bars up to 5,000, catalogue up to 1,000), sort, date ranges and batch calls for futures quotes and market status, with no field selection. The MCP server has 12 tools, 11 shown to the model. Massive and financial-datasets took 15 (15 of 25). limit, offset and next_offset, cursors on fundamentals and economic events, total_count on bars, search on symbols and updated_since on signals (18 of 20). Errors carry statusCode, message, a code, retryAfterMs, resetsAt, limitRps, plansUrl and the missing product or market, and the skill gives an action per status. Above financial-datasets' 16 (17 of 20). Every data call is a GET, and x402 settles only after a valid response with payment identifiers bound to the request, but no readOnlyHint or other annotation was found for the MCP tools. Financial-datasets took 14 without annotations (15 of 20). Data tools need only asset_class and symbol, with defaults for limit and sort, and official clients exist for JavaScript or TypeScript and Python, both at 0.1.0 from 20 October 2026. Stocks need the COUNTRY:TICKER form (14 of 15). 15+18+17+15+14 = 79.

Score by category

CategoryWeight this runFinancial DatasetsTickerLayerEdge
Reliability16%204370TickerLayer +27
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.28088TickerLayer +8
Agent ergonomics13%16.27379TickerLayer +6
Security & auth14%17.54949even
Payments & pricing10%12.57592TickerLayer +17
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.85679TickerLayer +23
Transparency & trust7%8.86338Financial Datasets +25
Negative events≤1500
TotalC 61.8/100BB 71.5/100

Facts side by side

FactFinancial DatasetsTickerLayer
KindHTTP APIHTTP API
VendorFinancial Datasets, Inc.TickerLayer
Hosted endpointhttps://api.financialdatasets.aihttps://mcp.tickerlayer.com/mcp
TransportsHTTP, Streamable HTTPHTTP, Streamable HTTP, websocket
AuthOAuth or keyOAuth or key
PricingPay per useFreemium
x402yes, from $0.02/callyes, from $0.01/call
LicencenoneProprietary hosted service under the TickerLayer terms of use, user agreement and market data disclaimer (all effective 3 November 2026), which name no legal entity or governing law. Free and Individual plans are for internal use, Business adds use inside the customer's own product, and redistribution needs a written Enterprise agreement. The agent plugin (github.com/tickerlayer/agent-plugin) and the npm client are MIT
Tools exposed2812
Read-only variant documentednono
llms.txtyesyes
MCP registrynot listedcom.tickerlayer/market-data
Last release2026-10-262026-11-06
Terms last updated2026-10-29not read yet
Privacy policy last updated2026-08-20not read yet
Customer content may train modelsnot found in the textnot read yet
Terms restrict automated accessyesnot read yet
Terms restrict benchmarkingyesnot read yet
Terms or service can change without noticenot found in the textnot read yet
Arbitration or class-action waivernot found in the textnot read yet

Verdicts

Financial Datasets

Every documented GET data endpoint takes x402 with no key, failed calls uncharged, and an agent can open and fund an account by API. A public OpenAPI file, llms.txt and a 28-tool OAuth MCP server cover the same data. There is no status page or free tier, keyed rate limits aren't published, and x402 data stops at 365 days.

TickerLayer

An agent can read quotes, bars and market hours across eight asset classes through a documented REST API, 12 MCP tools or 41 x402 resources with no account, and 429s carry Retry-After. The data is derived from unnamed non-exchange sources, no operator is named, and the status history couldn't be read.

Before you call either

Financial Datasets

  1. Without a key, read the price from the PAYMENT-REQUIRED header of the 402 and pay with x402 on Base; each page of next_page_url is a separate paid request
  2. Keep limit small and ask for one period at a time; premium endpoints count as 2, 4 or 8 requests on keyed plans
  3. Send the key only to api.financialdatasets.ai in the X-API-KEY header; on 401 ask the owner for a new key rather than signing up again
  4. Treat a 402 on a keyed account as an empty balance and mint a checkout link for the owner; don't retry the call
  5. Check the plan's licence before showing the data to anyone else; redistribution needs Professional or Enterprise

TickerLayer

  1. Write stocks as COUNTRY:TICKER, such as US:KO, and always pass asset_class to the data tools.
  2. If a 429 carries REST_QUOTA_EXCEEDED, stop and tell the user. Waiting doesn't reset the monthly quota.
  3. Present prices as indicative TickerLayer values, never as official exchange prices.
  4. Call get_market_status before you report a quiet symbol as missing data.
  5. Send the key in the x-api-key header, never as the apiKey query parameter.

Questions

Which is better for AI agents, Financial Datasets or TickerLayer?

TickerLayer scores 71.5 (BB) on agent readiness against Financial Datasets's 61.8 (C), and leads in 5 of 7 scored categories. Financial Datasets leads on transparency & trust.

Do Financial Datasets and TickerLayer need an API key?

Both take an API key or an OAuth sign-in. An agent can also pay Financial Datasets per call over x402, with no account. An agent can also pay TickerLayer per call over x402, with no account.

Can an agent call Financial Datasets and TickerLayer without installing anything?

Yes. Financial Datasets has a hosted endpoint at https://api.financialdatasets.ai and TickerLayer at https://mcp.tickerlayer.com/mcp.

Other comparisons with Financial Datasets or TickerLayer

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.