Exa API + MCP vs SpecStream

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.

SpecStream 23

Hosted reading, for the MCP server and REST API on api.specstream.ai. No public status page was found. None is linked from the site, llms.txt or the docs, llms-full.txt mentions none, and https://specstream.ai/status returned an error (0). No readable incident history, so the floor (5). No rate limit with numbers is published in the docs, llms.txt, llms-full.txt or the part of the OpenAPI file read; the privacy policy and DPA mention rate limiting without figures, and the published limits are per job (10,000 results a request, four-hour runs, 20,000 imported rows) (0). Nothing documents 429, Retry-After or backoff, but paid work requires an idempotency_key on authorize_capacity_work and POST /v1/capacity/executions, GET /v1/capacity/requests/{request_key} recovers the original find after an uncertain response, and the skills say never to quote again to recover a lost reply (8 of 15). No SLA on any plan, and the terms say 'We do not promise uninterrupted access' (0). No beta or preview label on the API, the MCP server or the SDKs, which PyPI classifies as production and stable at 1.2 (10). 0+5+0+8+0+10 = 23.

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).

SpecStream 65

MCP reading. 128 tools at about 143,700 characters of names, descriptions and schemas (more than 30, 5), with no server-side toolsets or dynamic loading; the framework packages for LangChain, LlamaIndex, CrewAI and the Vercel AI SDK and the Open WebUI tool expose two to four tools with the price cap held in code, and results default to short evidence (5 back, 10 of 25). Cursor and limit on rows, search, specs and revisits, evidence short or full, filters by area and by field on collections, and unconfirmed candidates kept in a separate list (18 of 20). An ErrorEnvelope on every operation and an SDK error class that exposes code and details, but no published code list, meanings or retry rules (6 of 20). Required idempotency keys on paid work, schedules and refund claims with a recovery route, expected_version on updates, stable event ids on webhook retries, and readOnlyHint on 72 tools and destructiveHint on 29, with no idempotentHint (18 of 20). compile needs only q, a quote needs only ast_hash with 25 results by default, and official SDKs in Python and TypeScript with a CLI, though one purchase takes three calls with a hash carried between them (13 of 15). 10+18+6+18+13 = 65.

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).

SpecStream 73

API keys ss_live_... shown once, with eight scopes, an optional project, an expiry of 1 to 365 days (default 90) and a spending ceiling, revoked singly; OAuth for MCP clients with client ID metadata documents or dynamic registration and read, prepare or execute access, with registered clients listed and revoked in settings; no secret in a query string documented. The authorisation server metadata on api.specstream.ai was not read and rotation is not described beyond expiry (28 of 30). Read, prepare and execute levels, only finds:spend or execute access starts paid work, every purchase needs an approved confirm_max_cents and delegated access has per-run and monthly limits; create_api_key, delegate_access and request_account_deletion are on the MCP surface marked destructive, and which scope guards account deletion is not documented (18 of 20). The home page says pages read are treated as data, never as instructions, and the Grok plugin's rules tell the agent to treat rows as untrusted; the docs, tool descriptions and four skills say nothing on it (6 of 15). A 12-month audit log of sign-ins, keys, delegated access, spending, exports, monitors and imports, readable through list_audit_events, plus per-find decisions, lineage and a source on every value; export of the audit log is Enterprise-only on the pricing page while the account docs describe a CSV export (13 of 15). security.txt is valid until October 2027 with support@specstream.ai, and SECURITY.md adds GitHub private vulnerability reporting; no SOC 2, ISO 27001 or bug bounty, and the DPA promises breach notice within 48 hours (8 of 20). 28+18+6+13+8 = 73.

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).

SpecStream 81

specstream-mcp-stdio 1.2.3 on PyPI on 3 November 2026, the Python SDK 1.2.0 committed the same day and @specstream/sdk 1.2.0 on npm on 31 October (30). Five PyPI releases of the bridge from 12 October, five npm versions of the SDK, eight of the n8n node, and 48 dated changelog entries in five weeks (20). A closed service with a dated changelog, support@specstream.ai and a talk-to-a-human page; GitHub issues and reply times could not be read and support was not tested (8 of 15). server.json under the reverse-DNS namespace ai.specstream/specstream 1.3.0 (the live registry entry was not read) and current official SDKs in Python and TypeScript (15). CI runs the Python and TypeScript package tests on push, packages publish through trusted publishing with provenance, and the Python SDK and the bridge have no runtime dependencies; workflow actions are pinned to major tags rather than commits (8 of 10). 30+20+8+15+8 = 81.

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).

SpecStream 80

MCP reading, with the REST API described. The tool list shipped in specstream-mcp-stdio 1.2.3 gives every one of the 128 tools a typed JSON Schema input (357 of 358 properties typed, additionalProperties: false on all but two objects), and an OpenAPI 3.1 file at https://specstream.ai/openapi.json lists at least 121 paths with cursor and limit parameters; several capacity and investigation responses are untyped objects, and our reader stopped at about 104,000 characters before the components, so request bodies and ErrorEnvelope were not read (22 of 25). llms.txt, llms-full.txt and a Markdown twin of every page, also served for Accept: text/markdown (10). Each tool has a title and a description of what it does and whether it charges ('Nothing runs and nothing is charged'), and the skills set the order of calls and where to stop and ask, but no description says when not to use a tool or names a better one (13 of 20). 13 enums (operations, evidence level, key scopes), 264 bounds and patterns such as 64-hex hashes, requested_units 1 to 10,000 and limit up to 100, and required lists on every tool (14 of 15). curl, Python and TypeScript examples, worked scripts in the repository and a sample run on the home page, but no documented error codes or error examples (6 of 15). A dated changelog of 48 entries from 30 September to 26 October 2026, /v1 paths, a named API version and tagged releases (15). 22+10+13+14+6+15 = 80.

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).

SpecStream 85

x402 v2 (USDC on Base, Arbitrum or Polygon, Permit2 upto for the quoted maximum, settled for the results cost) and MPP by card on SpecStream's own POST /v1/agent/lists, the route for buying a list of 1 to 500 results without an account; enrichment of imported lists, refreshes, monitors and investigations need an account, and the route was read in the docs and not exercised because api.specstream.ai's robots.txt could not be read, so partial (25). Per-result prices published without a login, 5, 15 or 100 cents a result, 5 cents an email, 15 cents a phone, rechecks at half rate or 1 cent (20). $10 of work for 30 days with no card (20). An agent can buy a list over x402 or MPP with no account, and the A2A endpoint prices a request without a key (20). 25+20+20+20 = 85.