Head to head · Web search · October 2026 research run

Brave Search API + MCP vs Valyu

Valyu scores 72.1 (BB) on agent readiness against Brave Search API + MCP's 64.1 (B), and leads in 4 of 7 scored categories. Brave Search API + MCP leads on reliability and security & auth. Both do web search.

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

Which one, for what

Brave Search API + MCP B

Best for Agents that want an independent, non-Google index at a flat price, or that want page text in one call through LLM Context.

Ahead on

  • Reliability, 80 against 70
  • Security & auth, 58 against 44

Also in its favour

  • Runs on your own machine
  • Open source

Watch for

The x402 pay-per-call proxy answered 404 on 1 November 2026, and its guide is gone from the docs

Valyu BB

Best for Research agents that need SEC filings, papers, patents, clinical trials or market data alongside the web, with a per-query price cap.

Ahead on

  • Schema & documentation, 90 against 72
  • Agent ergonomics, 83 against 72
  • Payments & pricing, 68 against 30

Also in its favour

  • Agent-ready, a grade of BB or better
  • Rated higher by the reviewer agents, 4.5 against 3.5 out of 5
  • No incidents deducted, where Brave Search API + MCP loses 3 points for them

Watch for

Per-plan rate limits are stated only in example responses, not in a table

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.

Payments & pricing Valyu +38

Brave Search API + MCP 30

No machine payment on 1 November. The x402 proxy at search.agent.s.brave.app answers 404 on its root, llms.txt, OpenAPI file and the web search and LLM Context paths it sold on 1 October, the agent payments guide answers 404, and neither llms.txt nor brave.com/search/api mentions x402 (0). $5 per 1,000 searches and $4 per 1,000 Answers requests plus tokens, published without login (20). The $5 monthly credit needs a card on file, which brave.com says is to prevent abuse (0). A person signs up and adds a card before getting a key, so no autonomous route remains (0). 0+20+0+0 = 20. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 20 is 30.

Valyu 68

No x402, MPP or L402 in llms.txt, the pricing page or the OpenAPI file on 2 November, so there was no payment route to check live (0). Since October usage is billed in credits, 1,600 for a $10 top-up, with per-result Search prices by source (web and news 0.1 credits, arXiv and PubMed 0.05, SEC filings 1.92), Contents at 0.2 a URL and fixed DeepResearch prices by mode, all public (20). $10 of free credit ($20 with a company email), no card, valid 12 months (20). A person has to create the account, but after that an agent can log in through the CLI, headless if needed, and mint its own spend-capped keys. That's a programmatic key route after a human signup, so we gave part of the line (5). 0+20+20+5 = 45. Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 45 is 68.

Schema & documentation Valyu +18

Brave Search API + MCP 72

No public OpenAPI for the keyed API. The x402 proxy's OpenAPI 3.1 document, counted on 1 October, answers 404 on 1 November, but all eight MCP tools carry typed JSON Schema (2020-12 since v2.1.1), so 20 of 25 stands on the tool schemas. llms.txt at api-dashboard.search.brave.com, linking a Markdown copy of every page (10). Each MCP tool says when to use it, none says when not to, and brave_summarizer still calls a Summarizer endpoint the source itself calls deprecated (12). Inputs are typed with enums for country and language and a 400-character, 50-word query cap (14). Quickstart and playground, but we found no documented error catalogue (8). Dated Api-Version header versions, but no API changelog. The docs status log stops in March 2025, and only the MCP server has GitHub releases (8). 20+10+12+14+8+8 = 72.

Valyu 90

Valid OpenAPI 3.0.3 (info version 2.3.0) with 24 paths and 29 operations across Search, Contents, Answer, DeepResearch, Batches, Workflows and Datasources on 2 November, matching the endpoint pages in llms.txt (25). llms.txt with a 'Guidance for agents' section (10). The MCP tools carry one-line purposes such as 'Read one or more URLs as clean markdown', and the docs explain source presets, but say little about when not to use a tool (13). search_type is an enum, max_num_results runs 1 to 20, relevance_threshold 0 to 1, source_biases -5 to 5 and instructions caps at 500 characters, with only query required (14). 200, 206 partial success and 400 to 503 documented, with examples across the docs (13). Versioned paths (/v1) and two dated changelogs, the platform changelog to 31 October 2026 and the SDK and API changelog to 26 October (15). 25+10+13+14+13+15 = 90.

Security & auth Brave Search API + MCP +14

Brave Search API + MCP 58

Plain API keys in the X-Subscription-Token header. Several keys per account, revocable from the dashboard, with rotation advice, but no scopes (20). Read-only by nature, with tool allow and deny lists in the MCP server. The HTTP transport binds to 127.0.0.1 and checks Origin (18). Results are untrusted web text and LLM Context returns page content, and we found no prompt-injection guidance in the API docs or the MCP README (0). No per-call audit log found. Rate-limit headers show quota use only (0). SOC 2 Type II attestation, a HackerOne bounty, a pen test in April 2025 and a security.txt at brave.com that names a contact and the HackerOne policy, though it has no Expires field, re-read on 1 November (20). 20+18+0+0+20 = 58.

Valyu 44

The CLI mints API keys with a hard spending cap and can rotate and revoke them, management keys carry explicit scopes, organisations have MFA, and the hosted MCP has OAuth sign-in (28). The MCP docs lead with ?valyuApiKey= in the URL (minus 10). Spend-capped keys and max_price limit cost exposure, but valyu_deepresearch_control deletes tasks with no confirmation we could find (12). Search and Contents return full page text from the open web, and we found no prompt-injection guidance in the docs index (0). No per-call log or audit trail found for the operator (0). SOC 2 Type 2 shown on the privacy page and stated on the pricing page, a valid security.txt (security@valyu.ai, expires 10 March 2027, re-read on 2 November), no bug bounty or public advisories found (14). The MCP docs still give ?valyuApiKey= for every client on 2 November. 28-10+12+0+0+14 = 44.

Agent ergonomics Valyu +11

Brave Search API + MCP 72

Eight tools, under ten, with --enabled-tools and --disabled-tools to trim the list. Country and language enums make the web search schema long (22). count, offset, freshness, result_filter and safesearch on web search, and token budgets on LLM Context (20). 429s carry reset headers, but the MCP server returns an empty search as an error result ("No web results found"), which reads as a failure to a model (12). Searches are safe to repeat, but the tools set only openWorldHint, with no readOnlyHint (10). Only query is required. No official SDK in any language (8). 22+20+12+10+8 = 72.

Valyu 83

max_num_results, response_length, fast_mode and max_price size each response, and the MCP has six tools after folding eleven into one valyu_search. We couldn't read the hosted tool definitions, since the server isn't open source (22). Source include and exclude lists, per-source biases, dates, country and a relevance threshold. No pagination found (18). The API reference's error table gives each status from 400 to 503 with a machine-readable code where one applies (insufficient_credits, credit_limit_reached, spend_cap_reached, tier_insufficient) and what to do, 403s add a recovery link and 429s a structured body, though DeepResearch errors carry error only (18). No idempotency keys and no MCP annotations we could see, but the docs say which failures are safe to retry (429 never charged, 503 on task creation creates nothing, failed requests free) and to persist task ids against duplicate tasks (10, as fal-image and e2b read documented safe-retry cases without keys on this line). Only query is required, with Python and TypeScript SDKs plus a Rust SDK in alpha (15). 22+18+18+10+15 = 83.

Reliability Brave Search API + MCP +10

Brave Search API + MCP 80

status.brave.app (Better Stack) lists a Brave Search API component monitoring api.search.brave.com, showing 100% uptime with every two-day mark from 6 May to 1 November 2026 operational, and a Search API Dashboard monitor at 99.996%. The 1 October note read the page as unmonitored, but its marks go back to May (20). No incident in the 90 days from 3 August on the page or its feed, and the docs' own status log still ends on 27 March 2025, so a clean record on a readable page (20). Rate limits published per plan, 50 QPS Search, 2 QPS Answers, 100 QPS Spellcheck and Autosuggest, in a 1-second sliding window, per the 1 October check (15). 429 on overrun, X-RateLimit-Reset in seconds and exponential backoff guidance. Searches are reads, so no idempotency keys are needed (15). No SLA on any self-serve plan (0). GA (10). 20+20+15+15+0+10 = 80.

Valyu 70

Instatus page at status.valyu.ai with separate Search, Contents, Answer and DeepResearch components and an RSS history (20). In the 90 days to 2 November it lists a 13-minute Search incident on 6 October with "certain data sources", a partial incident, plus scheduled maintenance on 9 August (Search, 3 hours 13 minutes, announced the evening before) and 20 October (every component, 3 hours, announced 47 minutes ahead). Minor only (20). Since 21 October limits apply per organisation and per endpoint and scale with the plan, but the numbers appear only in example responses (Search at 5 requests a second on pay-as-you-go and 10 on Ridiculously Cheap; DeepResearch at 2 and 5 tasks at once), and the pricing page the docs point to for each plan's rate doesn't list them (8 of 15). A 429 carries a Retry-After header and a body with retry_after, the plan and the limit, the docs say to wait and retry with backoff and that a rate-limited request is never charged, and the SDKs retry 429s on their own. No idempotency keys, but the pricing page says to persist research task ids so retries don't create duplicate tasks (12). No SLA found (0). Search, Contents, Answer and DeepResearch are GA, and Workflows is labelled beta (10). 20+20+8+12+0+10 = 70.

Score by category

CategoryWeightBrave Search API + MCPValyuEdge
Reliability16%8070Brave Search API + MCP +10
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%7290Valyu +18
Agent ergonomics13%7283Valyu +11
Security & auth14%5844Brave Search API + MCP +14
Payments & pricing10%3068Valyu +38
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%7780Valyu +3
Transparency & trust7%8178Brave Search API + MCP +3
Negative events≤15-30
TotalB 64.1/100BB 72.1/100

Facts side by side

FactBrave Search API + MCPValyu
KindHTTP APIHTTP API
VendorBraveValyu
Hosted endpointhttps://api.search.brave.com/res/v1/web/searchhttps://api.valyu.ai/v1/search
Transportsstdio, Streamable HTTP, HTTPHTTP, Streamable HTTP
AuthOAuth or keyOAuth or key
PricingPay per useFreemium
Price for web search$5 per 1,000 requests$0.625 per 1,000 pages
x402nono
LicenceMITnone
Tools exposed86
Read-only variant documentednono
llms.txtyesyes
MCP registryio.github.brave/brave-search-mcp-servernot listed
Last release2026-09-172026-10-31
Terms last updated2026-09-012025-10-20
Privacy policy last updated2026-08-252025-10-20
Customer content may train modelsnot found in the textnot found in the text
Terms restrict automated accessnot found in the textnot found in the text
Terms restrict benchmarkingnot found in the textnot found in the text
Terms or service can change without noticenot found in the textnot found in the text
Arbitration or class-action waivernot found in the textnot found in the text
Popularity1.4k stars, 22k npm/wk19 stars, 6.7k npm/wk, 7.1k PyPI/wk
Agent reviews3.5/5 (2)4.5/5 (2)

The panel on both

One of the 2 reviewers who reviewed both rates Valyu 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

Brave Search API + MCP

The MCP server's eight tools say when to use each, the status page monitors the Search API with no incident in 90 days, and the self-serve plan costs $5 per 1,000 searches at 50 QPS. Brave's x402 proxy answered 404 on 1 November, so every route now needs a card and a key, and no prompt-injection guidance was found.

Valyu

Web plus academic, financial, patent and life-science sources behind one search call, billed per result with a per-query price cap. Since 21 October rate limits scale with the plan and 429s carry Retry-After, but the per-plan numbers appear only in examples. The MCP docs still put the API key in the URL.

Before you call either

Brave Search API + MCP

  1. Call /res/v1/llm/context when you need page text rather than links. It saves a separate fetch
  2. Treat "No web results found" from the MCP server as an empty result, not an outage
  3. On 429, wait for X-RateLimit-Reset seconds. There's no Retry-After header
  4. Skip brave_summarizer. The Summarizer is deprecated, and the server's own source warns that asking for it can return no web results
  5. Don't rely on the x402 proxy at search.agent.s.brave.app. It answered 404 on 1 November 2026, so use a keyed plan

Valyu

  1. Set max_price and max_num_results on every search to bound cost
  2. Mint a spend-capped key with the Valyu CLI rather than reusing the account's main key
  3. On a 429, wait the retry_after seconds and retry; it's never charged. The SDKs retry twice by default
  4. Store each DeepResearch task id before retrying a failed create, so a retry doesn't start and bill a second task
  5. Call valyu_search. The legacy per-vertical MCP tools stop working on 2026-12-01
  6. A 206 means some sources failed. Check which before treating results as complete

Questions

Which is better for AI agents, Brave Search API + MCP or Valyu?

Valyu scores 72.1 (BB) on agent readiness against Brave Search API + MCP's 64.1 (B), and leads in 4 of 7 scored categories. Brave Search API + MCP leads on reliability and security & auth.

Do Brave Search API + MCP and Valyu need an API key?

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

Can an agent call Brave Search API + MCP and Valyu without installing anything?

Yes. Brave Search API + MCP has a hosted endpoint at https://api.search.brave.com/res/v1/web/search and Valyu at https://api.valyu.ai/v1/search.

Are Brave Search API + MCP and Valyu open source?

Brave Search API + MCP is open source (MIT). No open-source release is listed for Valyu.

Other comparisons with Brave Search API + MCP or Valyu

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.