SpecStream vs Tavily API + MCP

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.

Tavily API + MCP 90

incident.io status page at status.tavily.com with separate API, MCP and website components (20). One incident in the 90 days from 3 August, website degraded performance on 17 September 2026, and none since per the status feed re-read on 1 November. The API and MCP showed 100% per the 1 October check (30). Published limits, re-read on 1 November, 100 requests a minute on development keys and 1,000 on production, crawl 100 and research 20 task creations on both (15). 429 carries Retry-After and the docs say to use that value and the status code rather than parse the message. Since October a 434 tells non-paying plans that live fetching with max_age_hours is refused under load, with the advice to retry or omit it (15). The pricing page lists 'Enterprise-grade support and SLAs' for the custom Enterprise plan but publishes no SLA terms, per the 17 October check, and none were found in the docs index or terms (0). GA (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.

Tavily API + MCP 52

Revocable keys, separate development and production keys, and the Logs API filters by key, so several keys per account work. The hosted MCP adds OAuth but maps it to one dashboard key with no scopes (22). The MCP README and docs still lead with ?tavilyApiKey= in the URL on 1 November (minus 10). The five tools in the npm release all read. The GitHub main branch adds tavily_feedback, which posts scores to Tavily, the hosted server's tool list is unknown, and there's no read-only toolset (10). The home page says requests pass through 'security, privacy, and content validation layers that block PII leakage, prompt injection, and malicious sources'. That's a claim with no technical detail in the docs, plus a safe_search flag for adult content, per the 1 October check (7). The Logs API (filter by key and endpoint since August 2026) and include_usage give per-call visibility (13). SOC 2 and ISO 27001 named on the privacy page, per the 4 October check, and the MCP repo patches vulnerable dependencies about monthly (seven updates on 26 October). The trust centre is JavaScript-only for us (per the 1 October check, not re-read on 1 November), www.tavily.com/.well-known/security.txt returned 404 on 1 November, and no bug bounty found (10).

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.

Tavily API + MCP 81

Five tools in the published tavily-mcp 0.2.22 (npm, 5 August 2026, still the latest on 1 November), with about 11,900 characters of tool definitions in the source. The unreleased 0.2.23 on GitHub adds tavily_feedback and, since 27 October, longer search and extract descriptions and server instructions, about 13,300 characters for the five tools and 20,300 in all. We couldn't establish which version the hosted server runs, so the award stays. No tool filter found. Raw content, images and answers are opt-in, which keeps API responses small (18). max_results, domain include and exclude lists, time_range, start and end dates, country, and crawl depth, breadth and limit (20). 432 and 433 tell plan limits from pay-as-you-go limits, 434 marks flex tier capacity, and 401, 422 and 429 are documented separately. Over MCP, an API error in Tavily's {error: {code}} envelope (used for keyless caps) comes back as plain text without isError, and open issue #211 (5 September 2026) reported the same on a 401, per the 17 October check. The rendered text includes the retry time and next steps when the API sends them, so the award stays (20). No readOnlyHint or destructiveHint in the MCP source, re-read on 1 November. The five published tools only read, and failed extracts and maps aren't charged (8). Only query or urls is required, with official Python and JavaScript SDKs (15).

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.

Tavily API + MCP 90

Public OpenAPI at docs.tavily.com, and typed JSON Schema on every MCP tool (25). llms.txt with Markdown pages and a 'Start here for agents' section, re-read on 1 November (10). Tool descriptions say what each does and when to reach for it, such as search for facts past the model's cutoff, but the npm release doesn't say when not to. A commit of 27 October on the GitHub main branch adds some, such as using the news topic only when the user asks for news and leaving the extract query empty for tables, but it isn't released on npm, so the award stays (14). Enums for search_depth, topic, time_range and include_domains_mode, ranges for max_results (0 to 20 on the API, 5 to 20 in the MCP), chunks_per_source (1 to 3) and max_age_hours (-1 to 720), and caps of 300 included and 150 excluded domains. The feedback tool on the GitHub main branch, not in the npm release, takes free-form value fields (13). Error table with examples for 400, 401, 422, 429, 432, 433, 434 and 500, re-read on 1 November (15). Versioned SDKs and a monthly changelog, which on 1 November has an October 2026 section documenting max_age_hours (accepted values and the 434 flex tier) and Tavily CLI plain output, and the search API reference now documents max_age_hours. fetch_timeout appears only in the 434 example message and cache_fallback nowhere in the reference or changelog, and the API path isn't versioned (13).

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.

Tavily API + MCP 75

Official x402 at x402.tavily.com sells advanced search only, $0.01 in USDC on Base. An unpaid POST to /search returned 402 on 1 November with an x402 version 2 envelope offering the exact scheme on eip155:8453 for 10000 units (0.01 USDC), and a second agent-pay option on aws:base for 0.016, described as advanced mode. Extract, map, crawl and research aren't sold over x402 (15). Credit costs per endpoint and $0.008 a credit pay as you go, published without a login and unchanged on 1 November (20). 1,000 free credits a month, no card, re-read on 1 November (20). Keyless search and extract with the X-Tavily-Access-Mode: keyless header, plus the x402 route, so an agent needs no human signup (20).