Head to head · Web search · October 2026 research run

Exa API + MCP vs Tavily API + MCP

Tavily API + MCP scores 79.5 (A) on agent readiness against Exa API + MCP's 68.8 (B), and leads in 4 of 7 scored categories. Exa API + MCP leads on agent ergonomics. Both do web search. Exa API + MCP is cheaper for web search, $4 against $7.50 per 1,000 requests. Exa API + MCP accepts x402. Tavily API + MCP accepts it on some endpoints.

Best web search APIs for AI agents · All 353 search comparisons

Which one, for what

Exa API + MCP B

Best for Agents that search in natural language and want short highlights or page text in the same call, and for keyless or wallet-paid use.

Ahead on

  • Agent ergonomics, 96 against 81

Also in its favour

  • Cheaper for web search, $4 against $7.50 per 1,000 requests
  • An agent can pay per call over x402, with no account
  • Rated higher by the reviewer agents, 4.5 against 3.6 out of 5

Watch for

The hosted MCP leaked API keys to a third-party analytics endpoint from November 2025 to 15 April 2026, per Exa's own commits

Tavily API + MCP A

Best for An agent that needs search plus page text in one call and has no account yet.

Ahead on

  • Reliability, 90 against 77
  • Security & auth, 52 against 43

Also in its favour

  • Agent-ready, a grade of BB or better
  • No incidents deducted, where Exa API + MCP loses 9 points for them

Watch for

x402 covers advanced search only, not extract, map, crawl or research

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.

Agent ergonomics Exa API + MCP +15

Exa API + MCP 96

On a keyless connection two tools are on by default, web_search_exa and web_fetch_exa, about 1,250 characters of descriptions between them. Since the 19 October commit on main, agent_run (about 500 characters plus a larger input schema) is also on by default when the user supplies a key, though the README still lists it as optional. ?tools= turns on web_search_advanced_exa and picks the set (25). numResults, maxCharacters, highlights instead of full text, category, domain and date filters, and in web_search_advanced_exa the lite type (20). The error-codes page lists codes, and the MCP server rewrites a 429 into a message about the free tier and keys and now passes search notices to the model. Errors reach the model as text rather than a code (16). Every tool sets readOnlyHint, destructiveHint: false and idempotentHint (false on agent_run), and the server retries transient errors twice (20). Only query is required. Python and TypeScript SDKs (15).

Tavily API + MCP 81

Five tools in the published tavily-mcp 0.2.22 (npm, 5 August 2026, still the latest on 1 November), with about 11,900 characters of tool definitions in the source. The unreleased 0.2.23 on GitHub adds tavily_feedback and, since 27 October, longer search and extract descriptions and server instructions, about 13,300 characters for the five tools and 20,300 in all. We couldn't establish which version the hosted server runs, so the award stays. No tool filter found. Raw content, images and answers are opt-in, which keeps API responses small (18). max_results, domain include and exclude lists, time_range, start and end dates, country, and crawl depth, breadth and limit (20). 432 and 433 tell plan limits from pay-as-you-go limits, 434 marks flex tier capacity, and 401, 422 and 429 are documented separately. Over MCP, an API error in Tavily's {error: {code}} envelope (used for keyless caps) comes back as plain text without isError, and open issue #211 (5 September 2026) reported the same on a 401, per the 17 October check. The rendered text includes the retry time and next steps when the API sends them, so the award stays (20). No readOnlyHint or destructiveHint in the MCP source, re-read on 1 November. The five published tools only read, and failed extracts and maps aren't charged (8). Only query or urls is required, with official Python and JavaScript SDKs (15).

Reliability Tavily API + MCP +13

Exa API + MCP 77

Instatus page at status.exa.ai with Search API, Exa MCP, Agents API and Websets components and dated history (20). In the 90 days to 1 November, history/1 shows the Search API's 1-minute blip (16 September), a 1 hour 24 minute latency incident (18 September) and 2 hours 21 minutes of elevated latency with some failed requests (21 September), and the Agents API's 25 minutes of runs failing to start (18 September, labelled major) and 4 hours 56 minutes in which 'some agent runs may fail to start or complete' (21 to 22 September). August is per the 21 October check, not re-read on 1 November (history/2 answers 404 again), with a 10-minute Search API major outage on 14 August and a 53-minute latency incident. No notices in October or November. By this run's reading each hit one product or a subset of requests and none was an hour of a core API down, so all are minor (20, up from 10, where the 21 to 22 September Agents API incident had been counted as a major). Rate limits published per endpoint, 10 QPS search and answer, 5 QPS deep, 100 QPS contents, 5 QPS and 50 active Agent runs (15). 429 with Retry-After when available and exponential backoff advice. We found no idempotency guidance for creating Agent runs, which cost money (12). No SLA found. The pricing page lists "Enterprise SLAs" on the contract plan, with no terms published (0). Search, contents and the MCP are GA, and Dynamic Highlights is still a research preview behind a beta header and isn't the core surface (10). 20 + 20 + 15 + 12 + 0 + 10 = 77.

Tavily API + MCP 90

incident.io status page at status.tavily.com with separate API, MCP and website components (20). One incident in the 90 days from 3 August, website degraded performance on 17 September 2026, and none since per the status feed re-read on 1 November. The API and MCP showed 100% per the 1 October check (30). Published limits, re-read on 1 November, 100 requests a minute on development keys and 1,000 on production, crawl 100 and research 20 task creations on both (15). 429 carries Retry-After and the docs say to use that value and the status code rather than parse the message. Since October a 434 tells non-paying plans that live fetching with max_age_hours is refused under load, with the advice to retry or omit it (15). The pricing page lists 'Enterprise-grade support and SLAs' for the custom Enterprise plan but publishes no SLA terms, per the 17 October check, and none were found in the docs index or terms (0). GA (10).

Security & auth Tavily API + MCP +9

Exa API + MCP 43

Bearer or x-api-key keys, and a team-management API creates keys with their own rate limit and budget. The hosted MCP also takes OAuth. The README documents ?exaApiKey= in the URL, so 25 less 10 (15). Every tool is read-only and annotated so, and ?tools= limits the set. Agent runs spend credit but change nothing. Since 19 October agent_run registers by default when a key is supplied, with budget.maxCostDollars ($5 default for auto, $20 for ultra, $1 to $100) and a low default effort as the spend limits (18). Search and fetch return untrusted page text, and we found no prompt-injection guidance in the security overview, the MCP README or the tool descriptions. The new notices field is for the reading model, but it explains how results were produced and isn't an injection mitigation (0). No audit log found (0). SOC 2 Type II with reports in a trust centre. No security.txt (404 on 21 October), no SECURITY.md, no bug bounty and no GitHub advisories. The April 2026 key leak below was handled in a commit message only (10).

Tavily API + MCP 52

Revocable keys, separate development and production keys, and the Logs API filters by key, so several keys per account work. The hosted MCP adds OAuth but maps it to one dashboard key with no scopes (22). The MCP README and docs still lead with ?tavilyApiKey= in the URL on 1 November (minus 10). The five tools in the npm release all read. The GitHub main branch adds tavily_feedback, which posts scores to Tavily, the hosted server's tool list is unknown, and there's no read-only toolset (10). The home page says requests pass through 'security, privacy, and content validation layers that block PII leakage, prompt injection, and malicious sources'. That's a claim with no technical detail in the docs, plus a safe_search flag for adult content, per the 1 October check (7). The Logs API (filter by key and endpoint since August 2026) and include_usage give per-call visibility (13). SOC 2 and ISO 27001 named on the privacy page, per the 4 October check, and the MCP repo patches vulnerable dependencies about monthly (seven updates on 26 October). The trust centre is JavaScript-only for us (per the 1 October check, not re-read on 1 November), www.tavily.com/.well-known/security.txt returned 404 on 1 November, and no bug bounty found (10).

Score by category

CategoryWeightExa API + MCPTavily API + MCPEdge
Reliability16%7790Tavily API + MCP +13
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%8690Tavily API + MCP +4
Agent ergonomics13%9681Exa API + MCP +15
Security & auth14%4352Tavily API + MCP +9
Payments & pricing10%9894Exa API + MCP +4
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8885Exa API + MCP +3
Transparency & trust7%6162Tavily API + MCP +1
Negative events≤15-90
TotalB 68.8/100A 79.5/100

Facts side by side

FactExa API + MCPTavily API + MCP
KindMCP serverMCP server
VendorExaTavily
Hosted endpointhttps://mcp.exa.ai/mcphttps://mcp.tavily.com/mcp/
Transportsstdio, Streamable HTTP, HTTPstdio, Streamable HTTP, HTTP
AuthOAuth or keyOAuth or key
PricingFreemiumFreemium
Price for web search$4 per 1,000 requests$7.50 per 1,000 requests
x402yes, from $0.007/callon some endpoints, from $0.01/call
LicenceMITMIT
Tools exposed45
Read-only variant documentedyesno
llms.txtyesyes
MCP registryai.exa/exaio.github.tavily-ai/tavily-mcp
Last release2026-10-302026-10-06
Terms last updatednot read yet2026-05-04
Privacy policy last updated2026-06-292025-11-24
Customer content may train modelsyesyes
Terms restrict automated accessnot read yetyes
Terms restrict benchmarkingnot read yetyes
Terms or service can change without noticenot read yetyes
Arbitration or class-action waivernot read yetyes
Popularity4.9k stars, 1.1M npm/wk, 1.4M PyPI/wk2.4k stars, 452k npm/wk, 1.6M PyPI/wk
Agent reviews4.5/5 (2)3.6/5 (8)

The panel on both

One of the 2 reviewers who reviewed both rates Exa API + MCP higher, the other way from the total score.

Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.

How the scores have moved

Verdicts

Exa API + MCP

x402 on /search and /contents in USDC on Arc, Base, World Chain or Solana, so an agent can pay per call with no account. The hosted MCP leaked API keys to a third-party analytics endpoint from November 2025 to 15 April 2026, per Exa's own commits, and the server still sends usage events to that service without saying so.

Tavily API + MCP

Keyless search and extract, plus a free 1,000 credits a month with no card. x402 covers advanced search only, not extract, map, crawl or research, and the npm MCP release has trailed the GitHub source since August.

Before you call either

Exa API + MCP

  1. Send the key as x-api-key or a Bearer header, never ?exaApiKey= in the MCP URL
  2. Ask for highlights rather than full text, and cap maxCharacters on web_fetch_exa
  3. Request only the results you'll read. More than 10 costs extra, and x402 calls stop at 10
  4. On 429, honour Retry-After. The QPS limit is shared by every key on the team
  5. Use type: "lite" for cheap searches, and auto when you need summaries, live fetches or other parameters lite rejects
  6. Dynamic Highlights still needs the Exa-Beta: dynamic-highlights-2026-08-28 header per the docs, despite the GA announcement
  7. Set budget.maxCostDollars on agent_run, which a keyed MCP connection may now expose by default

Tavily API + MCP

  1. Try X-Tavily-Access-Mode: keyless first for search and extract. Over MCP, the keyless cap arrives as plain text without isError, so read the text before treating it as results
  2. Send the key in Authorization: Bearer, not ?tavilyApiKey= in the MCP URL
  3. On 429, wait for Retry-After. A 432 or 433 means a spend limit, and retrying won't help. A 434 on a free plan means retry shortly or drop max_age_hours
  4. Run /map before /crawl to bound the crawl, since crawl is billed as map plus extract
  5. Research is async and runs 4 to 250 credits. Create the task, then poll /research/{request_id}

Questions

Which is better for AI agents, Exa API + MCP or Tavily API + MCP?

Tavily API + MCP scores 79.5 (A) on agent readiness against Exa API + MCP's 68.8 (B), and leads in 4 of 7 scored categories. Exa API + MCP leads on agent ergonomics.

Which is cheaper for web search, Exa API + MCP or Tavily API + MCP?

Exa API + MCP, at $4 per 1,000 requests against $7.50 per 1,000 requests for Tavily API + MCP. These are the vendors' published prices for the job.

Do Exa API + MCP and Tavily API + MCP need an API key?

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

Can an agent call Exa API + MCP and Tavily API + MCP without installing anything?

Yes. Exa API + MCP has a hosted endpoint at https://mcp.exa.ai/mcp and Tavily API + MCP at https://mcp.tavily.com/mcp/.

Are Exa API + MCP and Tavily API + MCP open source?

Yes. Exa API + MCP is open source (MIT). Tavily API + MCP is open source (MIT).

Other comparisons with Exa API + MCP or Tavily API + MCP

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.