--- title: Conversational API Governance Your Agent Can Call description: API Governance MCP is an open-source Model Context Protocol server that lets AI agents lint API artifacts (OpenAPI, AsyncAPI, Arazzo, JSON Schema, etc.)... canonical: https://daily.dev/posts/conversational-api-governance-your-agent-can-call-xe9sb3wxl twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Conversational API Governance Your Agent Can Call | daily.dev og:description: API Governance MCP is an open-source Model Context Protocol server that lets AI agents lint API artifacts (OpenAPI, AsyncAPI, Arazzo, JSON Schema, etc.)... og:url: https://daily.dev/posts/conversational-api-governance-your-agent-can-call-xe9sb3wxl og:image: https://api.daily.dev/og/posts/Xe9Sb3wXL.png og:image:alt: Conversational API Governance Your Agent Can Call og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Conversational API Governance Your Agent Can Call **[API Evangelist](https://daily.dev/sources/apievangelist)** · 3 min read · 1 upvotes · 0 comments ## Summary API Governance MCP is an open-source Model Context Protocol server that lets AI agents lint API artifacts (OpenAPI, AsyncAPI, Arazzo, JSON Schema, etc.) against a 769-rule governance ruleset powered by Spectral. It exposes tools like lint_artifact, describe_rule, and validate_ruleset so agents can not only flag violations but explain why rules exist and suggest fixes. All rules default to info severity to educate rather than block, and custom rulesets can escalate specific rules. It runs locally over stdio, keeping specs and tokens on-machine, and installs via npx. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How do I lint an OpenAPI spec for governance issues using an AI agent instead of a browser tool? Install API Governance MCP with npx @api-common/api-governance-mcp and connect it to an MCP client like Claude Desktop. It runs the same Spectral engine and all-rules.yaml catalog (769 rules across 12 artifact formats) as the browser-based API Validator, exposing tools such as lint_artifact, describe_rule, and validate_ruleset so the agent can explain and help fix findings conversationally. _Developers wiring governance into agent workflows can track new MCP tooling releases like this on daily.dev._ ### Does an MCP-based API linter support Swagger 2.0 as well as OpenAPI 3.x? Yes, Swagger 2.0 is governed at full parity with OpenAPI 3.x. Spectral auto-detects each document's format and the server maps the swagger keyword to openapi internally, so an agent can reference either term and still apply the correct rule set. _Teams maintaining legacy Swagger 2.0 specs alongside newer OpenAPI docs can follow governance tooling updates on daily.dev._ ### What severity level do rules default to in the API Commons governance ruleset, and why? Every rule ships at info severity by default, reflecting a philosophy that governance should educate rather than block. Teams raise specific rules to warn or error only through their own custom Spectral ruleset, tailored to the conventions they actually want enforced. _Anyone deciding how strict to make API linting rules can follow governance tooling philosophy discussions on daily.dev._ ## Similar posts on daily.dev - [Put Governance Where the Agent Can Reach It](https://daily.dev/posts/put-governance-where-the-agent-can-reach-it-k16zuj5yc) · API Evangelist · 2 upvotes · 0 comments - [Your Governance Reaches the Pipeline. It Doesn't Reach the Conversation.](https://daily.dev/posts/your-governance-reaches-the-pipeline-it-doesn-t-reach-the-conversation--rehgyx3je) · API Evangelist · 1 upvotes · 0 comments - [MCP in action: What makes AI agents actually useful](https://daily.dev/posts/mcp-in-action-what-makes-ai-agents-actually-useful-xzn8qnwi5) · All Things Open · 0 upvotes · 0 comments - [Building effective AI agents with Model Context Protocol \(MCP\)](https://daily.dev/posts/building-effective-ai-agents-with-model-context-protocol-mcp--1k6pmnpvj) · Red Hat Developer · 1 upvotes · 0 comments - [How to Build AI Agents That Can Control Cloud Infrastructure](https://daily.dev/posts/how-to-build-ai-agents-that-can-control-cloud-infrastructure-yyzbrnqg9) · freeCodeCamp · 2 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#mcp](https://daily.dev/tags/mcp), [#openapi](https://daily.dev/tags/openapi) [View this post on daily.dev](https://daily.dev/posts/conversational-api-governance-your-agent-can-call-xe9sb3wxl) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Conversational API Governance Your Agent Can Call","url":"https://daily.dev/posts/conversational-api-governance-your-agent-can-call-xe9sb3wxl","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/conversational-api-governance-your-agent-can-call-xe9sb3wxl"},"datePublished":"2026-07-21T12:48:46.834Z","dateModified":"2026-09-14T07:01:56.286Z","description":"API Governance MCP is an open-source Model Context Protocol server that lets AI agents lint API artifacts (OpenAPI, AsyncAPI, Arazzo, JSON Schema, etc.)...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/f254060e8aea31241182cf69bde13002?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/f254060e8aea31241182cf69bde13002?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"API Evangelist","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"API Evangelist","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/a36244ae67bc4f41a605f780267ecb5f","url":"https://daily.dev/sources/apievangelist"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/conversational-api-governance-your-agent-can-call-xe9sb3wxl","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,mcp,openapi","timeRequired":"PT3M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"API Evangelist","item":"https://daily.dev/sources/apievangelist"},{"@type":"ListItem","position":3,"name":"Conversational API Governance Your Agent Can Call"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/conversational-api-governance-your-agent-can-call-xe9sb3wxl#faq","mainEntity":[{"@type":"Question","name":"How do I lint an OpenAPI spec for governance issues using an AI agent instead of a browser tool?","acceptedAnswer":{"@type":"Answer","text":"Install API Governance MCP with npx @api-common/api-governance-mcp and connect it to an MCP client like Claude Desktop. It runs the same Spectral engine and all-rules.yaml catalog (769 rules across 12 artifact formats) as the browser-based API Validator, exposing tools such as lint_artifact, describe_rule, and validate_ruleset so the agent can explain and help fix findings conversationally. Developers wiring governance into agent workflows can track new MCP tooling releases like this on daily.dev."}},{"@type":"Question","name":"Does an MCP-based API linter support Swagger 2.0 as well as OpenAPI 3.x?","acceptedAnswer":{"@type":"Answer","text":"Yes, Swagger 2.0 is governed at full parity with OpenAPI 3.x. Spectral auto-detects each document's format and the server maps the swagger keyword to openapi internally, so an agent can reference either term and still apply the correct rule set. Teams maintaining legacy Swagger 2.0 specs alongside newer OpenAPI docs can follow governance tooling updates on daily.dev."}},{"@type":"Question","name":"What severity level do rules default to in the API Commons governance ruleset, and why?","acceptedAnswer":{"@type":"Answer","text":"Every rule ships at info severity by default, reflecting a philosophy that governance should educate rather than block. Teams raise specific rules to warn or error only through their own custom Spectral ruleset, tailored to the conventions they actually want enforced. Anyone deciding how strict to make API linting rules can follow governance tooling philosophy discussions on daily.dev."}}]} ```