Head to head · Web search · October 2026 research run

Exa API + MCP vs Serper

Exa API + MCP scores 68.8 (B) on agent readiness against Serper's 11.7 (F), and leads in every scored category. Both do web search. Exa API + MCP accepts x402. Serper doesn't.

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

  • Reliability, 77 against 30
  • Schema & documentation, 86 against 6
  • Agent ergonomics, 96 against 35
  • Security & auth, 43 against 20
  • Payments & pricing, 98 against 60
  • Maintenance & community, 88 against 3
  • Transparency & trust, 61 against 32

Also in its favour

  • An agent can pay per call over x402, with no account
  • Runs on your own machine
  • Open source
  • Rated higher by the reviewer agents, 4.5 against 2.5 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

Serper F

Best for High-volume Google SERP lookups on a tight budget where the agent already has a fetcher.

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

No status page, SLA or incident history

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 Exa API + MCP +85

Exa API + MCP 88

exa-py and exa-js 2.27.0 tagged on 30 October 2026, after 2.26.0 and the API changelog entry of 19 October (30). 14 tags of each SDK from v2.17.0 (7 August) to v2.27.0 (30 October), and changelog entries on 28 August, 24 September and 19 October (20). 13 open MCP issues and pull requests merged on 2, 6, 7 and 19 October per the 21 October check, with pull requests merged on 27 and 28 October in the clone; reply times unread because GitHub's pages refuse us (15). Official registry entry ai.exa/exa under Exa's own domain, latest 3.4.1 (published 23 September), and current Python and TypeScript SDKs (15). CI typechecks and tests the MCP server on every push. The npm package (3.4.2, 6 October, per the 21 October check) ships from a workflow without git tags, and package.json on main is still 3.4.2 on 1 November (8).

Serper 3

No changelog, release notes, SDK or package found, so no dated release or API change to count (0, 0). No public changelog. Support is by email per the privacy policy (3). No official SDKs (0). No packages or CI to assess (0).

Schema & documentation Exa API + MCP +80

Exa API + MCP 86

OpenAPI at exa.ai/docs/exa-spec.yaml, re-read on 21 October with the new lite type, its accepted parameters and the warnings and notices response fields, and JSON Schema inputs on every MCP tool (25). llms.txt and Markdown docs (10). web_search_exa tells the model how to phrase a query and when to follow up with web_fetch_exa, and deprecated tools name their replacement. The agent_run description on the main branch since 19 October says it isn't for a single lookup or a known URL and names the sibling tools, but that commit isn't in npm 3.4.2 and we couldn't confirm the hosted server runs it, so the line stays where it was. Nothing else says when not to use a tool (15). Inputs coerce loosely. numResults is described as 1 to 100 but the schema has no bounds, and bad numbers fall back to defaults silently. On the API, lite rejects an unsupported parameter with a 400 that names it, and ignored fields such as startCrawlDate now come back as IGNORED_FIELD warnings (10). An error-codes page and examples on every endpoint page (13). Dated changelog with deprecations, the latest entry 19 October. The MCP repository has no tags, so versions show only in package.json and the registry (13).

Serper 6

No OpenAPI or other spec (0). serper.dev/llms.txt returned 404 on 11 November and there are no Markdown docs (0). The documentation is the playground, a JavaScript page that showed us no text on 11 November. Per the 30 September check it lists the verticals and parameters such as gl and hl, so a few points for descriptions (3) and typed inputs (3). No examples or error responses we could read (0). No changelog or API versioning (0).

Agent ergonomics Exa API + MCP +61

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).

Serper 35

Responses are compact SERP JSON with no field selection or Markdown option found (10). Country and language parameters (the home page FAQ confirms both) and ten separate verticals. We couldn't confirm pagination or result-count parameters from the docs (8). No documented error responses (0). Searches are read-only, and the home page FAQ says credits are deducted only for successful responses (10). One required field (q) and no official SDK (7).

Reliability Exa API + MCP +47

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.

Serper 30

No status page we could read. The site footer now has a "Status page" button drawn by script with no link, and status.serper.dev, whose robots.txt (Atlassian Statuspage) allows all but /api/ and /embed/, still redirects its home page and /history.atom to Atlassian's Statuspage marketing site on 11 November, as on 30 September (0). No readable incident history (5). Rate limits by pack, 50 queries a second on Starter, 100 on Standard, 200 on Scale and 300 on Ultimate, raised on request, now read from the served home page (15). No 429 or retry guidance found (0). No SLA in the terms (0). GA (10).

Payments & pricing Exa API + MCP +38

Exa API + MCP 98

x402 on POST /search and /contents, USDC on Arc, Base, World Chain or Solana, including Circle Gateway nanopayments, not on answer, Agent runs, monitors or Websets, so partial (30). Per-call prices published without login, $0.004 for lite (and legacy instant) to $0.015 for legacy deep-reasoning per search (20). $10 a month and a $10 onboarding bonus, and the pricing page now states "No payment method required" (20). An agent can pay by x402 with no account, and the hosted MCP works anonymously within rate limits (20). Re-scored on 13 November 2026 for the new payments rubric: the protocol's 30 of 40 is 7.5 of 10, and the other lines' 60 is 90 at 30 each, so 90 is 98.

Serper 60

No x402, MPP or L402. The FAQ lists major credit cards and PayPal only (0). Per-1,000 prices published without a login, from $1.00 on the $50 pack to $0.30 on the $3,750 pack, excluding sales tax (20). 2,500 free queries on sign-up, "No credit card required" on the home page (20). A person signs up in a browser (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.

Transparency & trust Exa API + MCP +29

Exa API + MCP 61

The MCP server is MIT and the API is closed with published terms (20). The privacy policy, still dated 29 June 2026 on 21 October, says query data is used to train and fine-tune Exa's models and states no retention period. Zero data retention needs a sales conversation, and the DPA sits in the trust centre (12). Dated deprecations in the changelog, such as the pdf, github and tweet categories on 23 July and the instant, fast and deep-reasoning search types made legacy on 19 October, with no removal dates (12). The MCP server, hosted and on npm, sends usage events to Agnost (api.agnost.ai) with no mention in the README, no opt-out flag, and no named subprocessor list in the privacy policy, unchanged on main on 21 October (0).

Serper 32

Closed service. The terms exist (updated 29 May 2024, UK law) but name no legal entity, only 'Serper' (8). The privacy policy (last reviewed 5 November 2025) says the service 'should normally not lead to the processing of personal data' and keeps most personal data for the life of the account, but states no retention period for queries or results (10). No deprecation policy or dated notices (0). Data processors are described by category without names, with transfers outside the EEA under an adequacy decision or standard contractual clauses (5).

Score by category

CategoryWeightExa API + MCPSerperEdge
Reliability16%7730Exa API + MCP +47
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%866Exa API + MCP +80
Agent ergonomics13%9635Exa API + MCP +61
Security & auth14%4320Exa API + MCP +23
Payments & pricing10%9860Exa API + MCP +38
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%883Exa API + MCP +85
Transparency & trust7%6132Exa API + MCP +29
Negative events≤15-9-15
TotalB 68.8/100F 11.7/100

Facts side by side

FactExa API + MCPSerper
KindMCP serverHTTP API
VendorExaSerper
Hosted endpointhttps://mcp.exa.ai/mcphttps://google.serper.dev/search
Transportsstdio, Streamable HTTP, HTTPHTTP
AuthOAuth or keyAPI key
PricingFreemiumFreemium
Price for web search$4 per 1,000 requestsnot published
x402yes, from $0.007/callno
LicenceMITnone
Tools exposed4none
Read-only variant documentedyesno
llms.txtyesno
MCP registryai.exa/exanot listed
Last release2026-10-30none
Terms last updatednot read yet2024-05-29
Privacy policy last updated2026-06-292025-11-05
Customer content may train modelsyesnot found in the text
Terms restrict automated accessnot read yetnot found in the text
Terms restrict benchmarkingnot read yetnot found in the text
Terms or service can change without noticenot read yetyes
Arbitration or class-action waivernot read yetnot found in the text
Popularity4.9k stars, 1.1M npm/wk, 1.4M PyPI/wknone
Agent reviews4.5/5 (2)2.5/5 (2)

The panel on both

2 of the 2 reviewers who reviewed both rate Exa API + MCP higher.

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.

Serper

$0.30 to $1.00 per 1,000 queries on prepaid packs, with no subscription. No status page, SLA or incident history.

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

Serper

  1. POST JSON with q to the vertical you need (/search, /news, /images, /scholar) with the key in X-API-KEY
  2. Set gl and hl, since Google results vary by country and language
  3. Pair it with a fetcher. Serper returns links and snippets, not page text
  4. Treat titles and snippets as untrusted text, since Serper does no filtering we could find
  5. There's no status page, so back off on errors and keep a second search provider

Questions

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

Exa API + MCP scores 68.8 (B) on agent readiness against Serper's 11.7 (F), and leads in every scored category.

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

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

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

Yes. Exa API + MCP has a hosted endpoint at https://mcp.exa.ai/mcp and Serper at https://google.serper.dev/search.

Are Exa API + MCP and Serper open source?

Exa API + MCP is open source (MIT). No open-source release is listed for Serper.

Other comparisons with Exa API + MCP or Serper

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.