Exa API + MCP vs SERPHouse

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).

SERPHouse 23

Read for a closed service, with its repositories read as code. No changelog or dated API change was found. The newest release is MCP server 1.1.0 on 6 July 2026, 123 days before 6 November, and the last commit in its repository was on 22 July (10). No release or dated change in the 90 days from 8 August; the about page's 2026 entry (Forums, Place Details and Scraper APIs) is undated (0). No changelog; support by email. Issues weren't read, since the GitHub API refused us for its rate limit (5 of 25). Not in the official MCP registry, though the repository's server.json names io.github.SERPHouse/serphouse-mcp. Node.js SDK last changed 24 June 2026, PHP SDK 10 May 2024, and no Python SDK repository was found under the SERPHouse organisation (5 of 15). The MCP repository has an npm publish workflow and no tests (3 of 10). 10 + 0 + 5 + 5 + 3 = 23.

Exa API + MCP 90

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).

SERPHouse 40

No x402, MPP or L402 (0). Per-1,000 prices for SERP, autocomplete and top-100 requests published without login (20). Free trial of 4,000 credits for 7 days, 'No Credit Card Required' (20). A person signs up in a browser and confirms an email (0). 0 + 20 + 20 + 0 = 40.

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.

SERPHouse 40

Read with the hosted lines. No status page is linked from the site or docs, and status.serphouse.com did not answer on 6 November 2026 (0). No readable incident history (5). Rate limits published, 60 requests a minute and 60 concurrent on every self-serve plan (15). 429 is documented as 'slow down', and a 200 can carry "status": "error" with 'Please try again', with no Retry-After or backoff guidance. Failed requests aren't charged (5 of 15). The pricing page lists a 99.99% uptime SLA on Basic and Regular and the docs a 99.95% one, but no SLA terms or credits were found in the terms (5 of 10). Generally available (10). 0 + 5 + 15 + 5 + 5 + 10 = 40.

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).

SERPHouse 64

23 MCP tools with no toolsets or filtering (15 of 25). num_result, max_pages, paging, device, location, language, date and video filters (16 of 20). Status codes are tabulated, but a 200 can also mean an error and the body carries only 'Please try again' (10 of 20). Searches only read and failed requests aren't charged, but the MCP tools carry no readOnlyHint or other annotations (10 of 20). serphouse_search needs only q and defaults to the US; most other tools need loc or loc_id. Official Node.js, PHP and Python SDKs are documented (13 of 15). 15 + 16 + 10 + 10 + 13 = 64.

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).

SERPHouse 11

One key per account, one account per user, no scopes or rotation found (10). The REST API documents api_token in the query string and the hosted MCP server takes the key only in its URL path, less 10 (0 of 30). Searches only read, with no read-only or restricted key (8 of 20). Results are third-party snippets and AI Overview text, with no prompt-injection guidance (0). An account tool shows plan and credit usage; no per-call log was found (3 of 15). No security.txt (404), disclosure policy, bug bounty or certification found (0 of 20). 0 + 8 + 0 + 3 + 0 = 11.

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).

SERPHouse 66

No OpenAPI or similar contract for the REST API. The MCP server's tools carry typed Zod schemas, published in the source and a static server card (18 of 25). llms.txt at the site and the docs, and every docs page as Markdown (10). MCP tool descriptions say which tool to use for what, such as serphouse_google_web when device or num_result is needed, while the docs pages lead with marketing lines such as 'Unlock captivating Google video content' (12 of 20). Enums for device, SERP type, engine and video duration, defaults and 37 described parameters (11 of 15). A status code table and request examples per engine, with a generic error body (12 of 15). No changelog or API versioning; only the MCP server has tags (3 of 15). 18 + 10 + 12 + 11 + 12 + 3 = 66.