Speakeasy provides an AI control plane platform that lets enterprises govern, secure, and observe AI agents, MCP servers, and Skills. The platform integrates with existing identity providers to assign permissioned identities to each agent and enforces policy in real time. It offers audit logs, compliance reporting, and deployment through existing MDM solutions for security, compliance, and AI enablement teams.
Speakeasy publishes 20 API contracts indexed on the APIs.io network, including Artifacts API, Auth API, CodeSamples API, and 17 more. Tagged areas include Artificial Intelligence, Documentation, MCP, Platform, and SDK.
The Speakeasy catalog on APIs.io includes 1 event-driven AsyncAPI specification, 1 JSON-LD context, and 2 Spectral governance rulesets.
Speakeasy’s developer surface includes CLI, support, API reference, authentication, documentation, engineering blog, changelog, and 59 more developer resources.
Regulatory Posture applies to this provider. Its tags matched the
Horizontal (data, software, accessibility, platform) regime, so
Regulatory Posture carries 15 points of the composite.
If this regime is wrong for your business, say so on your
provider repo — the
applicability map is public and we will correct it.
Create-or-Update Ergonomics applies to this provider. This API accepts writes, so it
carries 10 points of the composite. It is scored from the published contracts
themselves: whether a caller can create-or-update in one call, whether the write accepts a key the caller already
holds, and whether the response says which branch ran. Without that, every write needs a search-and-branch in
front of it, and the first time that check is skipped a duplicate record is created.
Scored against the observed mean rather than raw — a provider at the catalog average is unchanged by this facet,
not penalised by it.
The six quality facets above are damped to 75 points between them,
because the conditional facet above carries the other
25. That is why each facet's contribution is shown against a damped
maximum: raising a quality facet moves the composite by 75% of its nominal
weight, not 100%. The full arithmetic is at apis.io/rating/.
Show this score on your site.
It updates itself when the score changes. Paste this where you link to your API docs:
<a href="https://apis.io/providers/speakeasy/"><img src="https://apis.io/badge/speakeasy/card.svg" alt="Speakeasy on APIs.io — Kin Score by API Evangelist"></a>
Other styles, a README pill and a shields.io endpoint are on the badge page.
Raise your score.
Agent readiness — checks not met, largest first (exact, from this profile):
Idempotency+9 pts — OpenAPI mutating operations declare an idempotency key — a header, a request-body property, or a named de-duplication token whose own description says so (verified); else common[].type matches /idempoten/i (documented)
Documented Reversibility+6 pts — a reversal operation in the contract, graded up when a window is documented too
Pagination+5 pts — share of collection GETs (an array, or one wrapped in data/items/results ...) that declare a page/limit/offset/cursor parameter, a Link header or a next/cursor field; na with no collection GETs
Agentic Commerce Well-Known Document+5 pts — a parsing /.well-known/ucp.json or acp.json declaring a version and at least one service — `self` when its endpoints are on the provider's own domain, `platform` when they are on a vendor's
Speakeasy is an area vendor: providers adopt it to run part of their developer surface. This is the Kin Score checks its features can move for a provider that adopts it, what each one really earns, and what it earns nothing for.
sdk generationcapability map11 features checked 2026-09-25 · rubric v0.22.0
Speakeasy moves Developer Ergonomics through SDKs in seven languages and a generated Go CLI, and each counts only once the provider declares it in apis.yml. It is one of the few vendors whose output is an OpenAPI Overlay (the x-codeSamples code-samples overlay), which scores overlay_published if the provider publishes it. Those code samples are SDK snippets, not request/response examples, so they earn nothing on examples_present and only the link fallback on openapi_examples. Its MCP servers, Terraform providers and retry logic look like the customer’s own work, so the customer surface carries almost no Speakeasy fingerprint.
Agent Readiness7.8 of 139 pts
Contract Governance4.0 of 33 pts
Contract Quality21.0 of 211 pts
Developer Ergonomics10.0 of 42 pts
Check
Earns
Through
MCP Serverdocumented Agent ReadinessTools are generated per operation from the provider’s own OpenAPI, so their shape should not cluster with other customers’ as platform. A Gram server left on Gram’s default URL is not on the provider’s surface.
Request/Response Examplespartial Agent Readinessx-codeSamples are SDK usage snippets, not request/response examples. The dimension reads examples first, so Speakeasy reaches only the Code Samples link fallback (0.25).
Publishes an OpenAPI Overlay Contract GovernancePublish the code-samples Overlay document where the catalog harvests overlays/. By default it sits in the Speakeasy registry and the provider’s workflow, not on the provider’s public surface.
Unique operationIdssaturated Contract QualityOnly when the provider fixes what the generation ruleset flags and publishes that contract. The linter does not rewrite the document.
Keeps credentials out of the query stringconditional Contract QualityThe owasp ruleset flags query-string credentials. Clearing it means changing how the API authenticates, not the document.
Across 8977 providers that publish a contract, adopting Speakeasy would move 8976. Median lift: composite +6.9 (90th percentile +6.9), agent readiness +4.4 (+5.6). Conditional rows excluded.
What Speakeasy ships that earns nothing (4)
Code samples delivered as an OpenAPI Overlay — x-codeSamples are SDK snippets. The check counts request or response examples on operations.
SDK retries driven by x-speakeasy-retries — Retries reuse an idempotency header only when the contract already declares one. The SDK never adds one.
Speakeasy Agent Skills — The skills teach an agent to use Speakeasy. They describe nothing on the customer’s API.
OpenAPI linter — A .speakeasy/lint.yaml is private workflow configuration. The check reads a ruleset the provider publishes.
A model, not a score. Adopting this vendor changes a provider's Kin Score only when the provider publishes the resulting artifacts on its own surface; nothing here writes a score, and no sponsorship or partnership can. The rating is not for sale → · Full vendor facets artifact
Markets this provider is in provisional
The Kin Score Market layer reads a provider inside its market:
its position, and how deep its integrations go. Depth is only comparable within a position. Provisional and unweighted:
not part of the Kin Score or agent readiness.
Registered MCP server and declares compatibility are report only — not weighted.
Undeclared means we found nothing we can read, so there is no number: we never infer integrations.
Standards this provider implements or carries. De facto ones are profiled and measured by the API Commons; formal ones come from the standards directory and are linked by the provider's own tags. The evidence column says how each claim was established — not that it was made.
Generate idiomatic, type-safe SDKs in 7+ languages from OpenAPI specs. Supports TypeScript, Python, Go, Java, C#, PHP, Ruby, and more with automated CI/CD integration and publis...
Turn your OpenAPI spec into a production-ready Terraform provider without the manual work. Automatically keeps providers synchronized with API changes, eliminating manual drift.
Generate production-ready MCP server code from OpenAPI specifications. Deploy on your own infrastructure, customize to your needs, and distribute however you want. Supports Clou...
Generate beautiful API documentation from OpenAPI specs. Automatic synchronization keeps docs current with every API change. Works with Docusaurus, Nextra, or any React and Mark...
API contract test generation using OpenAPI specs and the Arazzo specification. Generates both test code and test data needed to validate API behavior in native testing framework...
Turns your OpenAPI spec into fully typed TanStack Query hooks with built-in caching, retries, and pagination, delivered in idiomatic React with zero config required.
The MCP Cloud platform by Speakeasy. Ship better agents with production-ready MCP infrastructure. Host remote MCP servers, power in-application chat, and manage and secure MCP s...
Yes. APIs.io lists 20 APIs from Speakeasy, including Speakeasy SDK Generation, Speakeasy Terraform Generation and Speakeasy MCP Server Generation, and 17 more.
Is there an OpenAPI specification for the Speakeasy API?
Yes. APIs.io indexes 13 OpenAPI specifications for Speakeasy, each linked for download from this page.
How do I authenticate with the Speakeasy API?
Speakeasy documents its authentication (apiKey/http · 3 schemes). The details are profiled on APIs.io as Speakeasy Authentication.
How much does the Speakeasy API cost?
APIs.io lists 5 pricing plans for Speakeasy, with each plan's price, limits and inclusions under Pricing Plans on this page.
Does Speakeasy have an MCP server?
Yes. APIs.io lists 1 MCP server for Speakeasy: Remote MCP server at app.getgram.ai over HTTP.
Is the Speakeasy API ready for AI agents?
Speakeasy has a Kin Score of 72.6 out of 100 (exemplar) and an Agent Readiness score of 52.5 (agent-ready), scored by API Evangelist on 2026-11-02.
Discovery needs no key. Ratings and market analysis are Pro.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we
store it to create your key and to recognise you if you sign in with another
provider. See our Privacy Policy and
Terms.