◎ Discry Score
parallel.com
ai · API
A
0 / 100
DISCOVERY0
COMPREHENSION0
Category leader: 99 (A)
Discry your API →
AI · RANK #16 OF 43

Parallel is Agent-Ready to agents.

Discry independently scored how well an AI agent can discover and understand the Parallel API from what’s public — not whether it’s usable. Below: every signal we checked, what’s costing the score, and what to change.

Discry your API — freeView the docs ↗

SCORED UNDER RUBRIC 1.2 · A full re-launch under Discry Score 2.5 — a new behavioral instrument, not comparable to these scores — is in progress.

Discovery

45% of score · 88/100
OpenAPI specA machine-readable OpenAPI/Swagger spec agents can parse.Pass
llms.txtAn llms.txt index that points agents to the docs that matter.Pass
llms.txt qualityThe llms.txt is focused, current, and well under the size budget.Pass
llms-full.txtA full-text bundle agents can load in one request.Pass
AGENTS.mdAn AGENTS.md that tells coding agents how to build on the API.Partial
.well-known/mcp.jsonA discoverable MCP manifest at a well-known path.Fail
MCP registryThe API is listed in a public MCP registry.Pass
robots.txt AI directivesrobots.txt allows (or explicitly guides) AI crawlers.Pass
SitemapA sitemap so agents can enumerate the docs surface.Pass

Comprehension

55% of score · 96/100
Task-oriented descriptionsEndpoints described by what they accomplish, not just their shape.Pass
Realistic examplesRunnable, real-world request/response examples.Pass
Multi-step workflowsDocs that chain calls into complete jobs an agent can follow.Pass
Error-recovery guidanceDocumented failure modes and how to recover from them.Partial
Answer-first formatThe answer leads; preamble does not bury it.Pass
Capability boundariesClear limits — what the API can and cannot do.Pass
Naming consistencyConsistent, predictable naming across endpoints.Pass
Heading hierarchyClean heading structure agents can navigate.Pass
Markdown docsDocs available as clean markdown, not JS-rendered HTML only.Pass
Token efficiencyDocs are concise enough to fit an agent context window.Pass

What we found

  • Parallel is the most agent-native API scanned — the entire documentation is built around agent consumption with setup prompts designed to be copy-pasted directly into coding agents, tool definitions in OpenAI format, and explicit TypeScript/Python SDK notes
  • The llms.txt and llms-full.txt are exemplary: API-focused, right-sized, structured by product, with every page fetchable as markdown via .md suffix or Accept header — agents can consume the entire API surface in a single fetch
  • Official MCP servers for Search and Task are listed on PulseMCP, Smithery, and Glama with OAuth flow support (no API key setup required for Search) — the lowest-friction agent integration path of any API scanned
  • The overview page serves as both human documentation and agent onboarding: setup prompts for each product include tool definitions, SDK install commands, and complete working examples that agents can directly implement
  • Documentation explicitly addresses the agent developer persona with notes like 'Don't let your linter camelCase body fields — the call will fail' and 'Mixed casing is load-bearing' — practical guidance that prevents common agent integration failures

What to change

Prioritized by impact on discoverability. You (or your docs platform) deploy these — Discry never touches your API.

  1. 01Add .well-known/mcp.json at docs.parallel.ai or parallel.ai pointing to the official Search and Task MCP servers
  2. 02Upgrade agents.md from CLI setup instructions to a comprehensive AGENTS.md covering API capabilities, when to use each product, and common integration patterns for coding agents
  3. 03Add explicit error recovery guidance for common failure modes across all APIs (rate limits, auth failures, timeout handling for long-running Task API calls)
  4. 04Consider adding AGENTS.md to the parallel-web GitHub org repos (parallel-sdk-python, parallel-web-tools) for coding agent discovery

Execution coverage · INFORMATIONAL, UNSCORED

Whether an agent can actually complete a call and recover from errors is the deeper Audit layer — documented here, but not part of the Discry Score.

api_keyoauth2✓ Error format documented✓ Rate limits documented✓ Pagination documented✕ Idempotency documented

API key authentication via PARALLEL_API_KEY environment variable. OAuth flow available for MCP server connections (no API key needed for Search MCP). JSON error responses with error_type field. Webhook signature verification documented for Monitor API (HMAC-SHA256). SDKs in Python (parallel-web) and TypeScript (parallel-web). No explicit idempotency documentation.

See your own Discry Score.

Drop your API docs URL. See what an agent sees — in 60 seconds, free.

Discry your API — free