# Exa API + MCP vs Mojeek Web Search API (slim)

> Exa scores 67.8 (B) to Mojeek Web Search's 36.4 (F) for web search. Mojeek Web Search is cheaper for web search, $2.68 against $4 per 1,000 requests. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/exa-mcp-vs-mojeek.md (~6,100 tokens) · this version ~3,530 tokens · JSON https://www.anchorterminal.com/compare/exa-mcp-vs-mojeek.json · canonical https://www.anchorterminal.com/compare/exa-mcp-vs-mojeek
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-07
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Exa API + MCP scores 67.8 (B) on agent readiness against Mojeek Web Search API's 36.4 (F), and leads in 6 of 7 scored categories. Mojeek Web Search API leads on transparency & trust. Both do web search. Mojeek Web Search API is cheaper for web search, $2.68 against $4 per 1,000 requests. Exa API + MCP accepts x402. Mojeek Web Search API doesn't.

- Exa API + MCP: B 67.8, rank #304 of 1510 · https://www.anchorterminal.com/tools/exa-mcp.min.md
- Mojeek Web Search API: F 36.4, rank #1387 of 1510 · https://www.anchorterminal.com/tools/mojeek.min.md
- Exa API + MCP, good 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 45; Schema & documentation, 86 against 29; Agent ergonomics, 96 against 66; Security & auth, 43 against 15; Payments & pricing, 90 against 20; Maintenance & community, 88 against 10. Also An agent can pay per call over x402, with no account; A hosted endpoint, with nothing to install; Runs on your own machine; Free to start without a card; Open source.
- Mojeek Web Search API, good for Agents and products that want a second, independent index beside Google-derived results, or European data handling with no sub-processors. Ahead on Transparency & trust, 68 against 61. Also Cheaper for web search, $2.68 against $4 per 1,000 requests; No incidents deducted, where Exa API + MCP loses 9 points for them.

| Category | Exa API + MCP | Mojeek Web Search API |
| --- | --- | --- |
| Reliability (16%) | 77 | 45 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 86 | 29 |
| Agent ergonomics (13%) | 96 | 66 |
| Security & auth (14%) | 43 | 15 |
| Payments & pricing (10%) | 90 | 20 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 88 | 10 |
| Transparency & trust (7%) | 61 | 68 |

| Fact (where they differ) | Exa API + MCP | Mojeek Web Search API |
| --- | --- | --- |
| Kind | MCP server | HTTP API |
| Vendor | Exa | Mojeek Limited |
| Hosted endpoint | `https://mcp.exa.ai/mcp` | no (local only) |
| Transports | stdio, Streamable HTTP, HTTP |  |
| Auth | OAuth or key | API key |
| Pricing | Freemium | Pay per use |
| Price for web search | $4 per 1,000 requests | $2.68 per 1,000 requests |
| x402 | yes, from $0.007/call | no |
| Licence | MIT | none |
| Tools exposed | 4 | 0 |
| Read-only variant documented | yes | no |
| llms.txt | yes | no |
| MCP registry | `ai.exa/exa` | not listed |
| Last release | 2026-10-30 | none |
| Terms last updated | not read yet | no date given |
| Privacy policy last updated | 2026-06-29 | 2022-02-02 |
| Customer content may train models | yes | not found in the text |
| Terms restrict automated access | not read yet | not found in the text |
| Terms restrict benchmarking | not read yet | not found in the text |
| Terms or service can change without notice | not read yet | yes |
| Arbitration or class-action waiver | not read yet | not found in the text |
| Popularity | 4.9k stars, 1.1M npm/wk, 1.4M PyPI/wk | none |
| Agent reviews | 4.5/5 (2) | none |

Why the edge:
- Maintenance & community, Exa API + MCP +78: 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).); Mojeek Web Search API 10 (Read for a closed service. No API changelog, release notes or dated API change were found, and the blog's posts since 2024 are about search in general, so the last change can't be dated (0). No dated changes in the 90 days from 8 August (0). A staff member answered API questions on the community forum within a day in December 2025 and October 2026, and support is by email; no public changelog (10 of 15). No official SDKs or MCP server (0). No public packages or CI to measure (0). 0 + 0 + 10 + 0 + 0 = 10.)
- Payments & pricing, Exa API + MCP +70: 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).); Mojeek Web Search API 20 (No x402, MPP or L402 (0). Per-request prices published without login, £2 and £3 per 1,000 requests (20). The FAQ says a free credit comes with the Startup plan, but a bank card is required to open an account (0). A person signs up in a browser and adds a card (0). 0 + 20 + 0 + 0 = 20.)
- Schema & documentation, Exa API + MCP +57: 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).); Mojeek Web Search API 29 (No OpenAPI or other machine-readable contract (0). No llms.txt (404) and no Markdown pages for agents (0). The parameters page states what each parameter does, with notes on when not to use `reg` and `clufmt`, but nothing on when another endpoint fits better (12 of 20). Every parameter has a type, defaults and valid ranges (tlen 0 to 127, dlen 0 to 511, rbb and lbb 1 to 100, up to 25 domains), though `reg` is called an enum without listing its values (11 of 15). One curl example and annotated JSON and XML response formats; errors appear only as a `status` string with one example (6 of 15). No API version, changelog or dated release notes, and the quickstart and the parameters page give different hosts (0). 0 + 0 + 12 + 11 + 6 + 0 = 29.)
- Reliability, Exa API + MCP +32: 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.); Mojeek Web Search API 45 (Read with the hosted lines. status.mojeek.com is a Site24x7 StatusIQ page with Search, Website, Blog and Community components. It is drawn by script, so only its RSS feed could be read, which shows each component's current state (Search operational since 7 September 2026) and no incident entries (15 of 20). No readable incident history (5). Rate limits are published per plan, 5 a second and 100,000 a day on Startup, 10 a second and 400,000 a day on Business (15). Over the daily limit the JSON `status` reads 'ERROR: Daily Limit Reached'; no HTTP 429, Retry-After or backoff guidance was found (0). No SLA, and the API terms say the service is provided as is and may be interrupted without notice (0). Generally available, with only the `lr` parameter marked beta (10). 15 + 5 + 15 + 0 + 0 + 10 = 45.)
- Agent ergonomics, Exa API + MCP +30: 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).); Mojeek Web Search API 66 (Responses can be sized with `t` (up to 10, 40 or 100 results by plan), `tlen`, `dlen` and opt-in date and size fields (22 of 25). `s` for paging, `since` and `before`, `site`, included and excluded domains, region and language boosting and safe search (20). Errors are a free-text `status` with no documented codes, which an agent can't branch on reliably (5 of 20). Searches only read, so a retry is safe, but no page says whether failed or empty requests are billed (12 of 20). Only `q` and `api_key` are required, with recommended values for the boosts. No official SDK in any language (7 of 15). 22 + 20 + 5 + 12 + 7 = 66.)
- Security & auth, Exa API + MCP +28: 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).); Mojeek Web Search API 15 (One key per account, documented only as the `api_key` query parameter, and rotation or revocation is by email to the API team (a staff reply of 22 October 2026 on the community forum asks for the key's last 8 digits). One all-powerful key (10) less 10 for the key in the URL (0). Search is read-only and there is nothing to write, but no scoped or restricted key (10 of 20). Results are third-party titles and snippets, with no prompt-injection guidance found (0). No audit log or per-call usage view was found in the docs; the FAQ mentions budget alerts on the account (0 of 15). security.txt names security@mojeek.com, with no Expires field. No bug bounty, disclosure policy, SOC 2 or ISO 27001 found; the API page claims compliance with European rules such as the EU Data Act without a certification (5 of 20). 0 + 10 + 0 + 0 + 5 = 15.)