◎ Discry Score
mongodb.com
infrastructure · API
C
0 / 100
DISCOVERY0
COMPREHENSION0
Category leader: 98 (A)
Discry your API →
INFRASTRUCTURE · RANK #50 OF 68

MongoDB is Needs Work to agents.

Discry independently scored how well an AI agent can discover and understand the MongoDB 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 · 64/100
OpenAPI specA machine-readable OpenAPI/Swagger spec agents can parse.Pass
llms.txtAn llms.txt index that points agents to the docs that matter.Partial
llms.txt qualityThe llms.txt is focused, current, and well under the size budget.Partial
llms-full.txtA full-text bundle agents can load in one request.Fail
AGENTS.mdAn AGENTS.md that tells coding agents how to build on the API.Fail
.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 · 65/100
Task-oriented descriptionsEndpoints described by what they accomplish, not just their shape.Partial
Realistic examplesRunnable, real-world request/response examples.Partial
Multi-step workflowsDocs that chain calls into complete jobs an agent can follow.Partial
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.Partial
Token efficiencyDocs are concise enough to fit an agent context window.Partial

What we found

  • MongoDB maintains a well-organized OpenAPI spec repo (github.com/mongodb/openapi) with SDKs auto-generated from it — a strong foundation for agent tooling, but the discovery layer above it is underdeveloped
  • The llms.txt at mongodb.com is product-focused ('MongoDB is the world's leading modern database') rather than API-focused — an agent looking for Atlas Admin API integration guidance would need to navigate multiple hops to find actionable content
  • MongoDB has invested heavily in agent-adjacent tooling (agent-skills repo, ADK agents, Postman workspace) but hasn't connected these to standard discovery signals like AGENTS.md or .well-known/mcp.json
  • The Atlas API documentation hub lists 10 programmatic access methods (API, Go SDK, CLI, Terraform, CDK, CloudFormation, Kubernetes Operator, etc.) which is comprehensive but creates decision paralysis for an agent trying to choose the right integration path
  • Community MCP servers exist on Glama and Smithery but no official MongoDB-maintained MCP server was found

What to change

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

  1. 01Rewrite llms.txt to be API-focused — cover the Atlas Admin API, Data API, and Embedding API with structured descriptions and endpoint summaries instead of product marketing
  2. 02Add llms-full.txt with comprehensive Atlas API documentation in markdown format
  3. 03Add AGENTS.md to mongodb/openapi or mongodb/agent-skills repos pointing agents to the right integration path based on use case
  4. 04Publish .well-known/mcp.json at mongodb.com or docs domain pointing to recommended MCP server tooling
  5. 05Create a decision tree in documentation: 'Building an agent? Use the Atlas Admin API + Go SDK. Need data access? Use the Data API. Need search? Use Atlas Vector Search.'

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

Atlas Admin API uses digest authentication or API keys. Go SDK and CLI available as alternative interfaces. Rate limits documented. Pagination supported. JSON error responses. Terraform, CloudFormation, and Kubernetes operator provide IaC access patterns. No idempotency documentation found.

See your own Discry Score.

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

Discry your API — free