Clawvisor
Clawvisor is the authorization layer for AI agents — a Y Combinator (Spring 2026) security gateway that sits between an AI agent and the tools it acts on (Gmail, Calendar, Drive, Contacts, GitHub, Slack, Notion, Linear, Stripe, Twilio, iMessage). Agents never hold downstream credentials: they declare a task describing their purpose and the service/action pairs they need, the user approves that scope once, and Clawvisor enforces restrictions, task scope, and LLM intent verification on every request before injecting vaulted, short-lived credentials, executing through an adapter, and writing a full audit trail. It ships open-core as a self-hostable Go daemon with a CLI, web dashboard, TUI, and an OAuth 2.1 MCP server, plus an official Claude Code plugin. Agents integrate over a plain HTTP gateway or MCP — no SDK or agent-code changes required.
Real signal across most facets with visible, nameable gaps — the contract exists but is thin, or the portal is good while governance and commercial terms are absent.
API Evangelist profiles Clawvisor the way a machine reads it — 12 machine-readable artifacts across 5 APIs, pulled from the provider's own public surface and indexed so a developer, an analyst, or an AI agent can evaluate it against every other provider on the network.
Every provider in the network is reduced to the same set of machine-readable artifacts — OpenAPI contracts, event specifications, GraphQL schemas, runnable collections, pricing and rate-limit signals, security posture, OAuth scopes, and the agent surfaces (MCP servers and skills) that let software drive the API on its own. We profile them because the interface is the part of a company you can actually inspect: it is a truer signal of what a provider does than any marketing page. From those artifacts we compute the Kin Score — Clawvisor scores 51.2/100 (developing), with a separate agent-readiness read of 75/100 (agent native). The full breakdown is below, followed by every artifact we hold — each card links through to its machine-readable definition on apis.io.
Kin Score
This is the API Evangelist rating — a single, repeatable read computed from the artifacts on this page. Green fill is points earned; the red track is points possible, so every bar shows earned-versus-possible at a glance.
Kin Score
How this is scored →scored 2026-07-27 · rubric v0.5
How we profile Clawvisor
Each block below is one kind of artifact we hold for Clawvisor. For each we say what it is and why it earns a place in the profile, then list every one we've indexed — capped at two rows, scroll within the panel for the rest.
APIs 5
Each API is captured as its own OpenAPI definition — every operation, parameter, and response. This is the single most useful machine-readable description of what an API does, and it's what lets us score, lint, mock, and generate against it without asking the provider for anything.
Individual APIs this provider publishes, each with its own machine-readable definition.
Clawvisor Auth API
Local magic-link session exchange.
Clawvisor Catalog API
Discover the services and actions available to the agent.
Clawvisor Gateway API
Execute authorized actions on downstream services through the gateway.
Clawvisor Tasks API
Declare, approve, expand, and complete task scopes.
Clawvisor Tokens API
Mint and revoke scoped agent tokens (admin-gated).
Arazzo Workflows 2
Real integrations are rarely a single call. Arazzo describes the multi-step sequences — auth, then create, then confirm — so both a human and an agent can follow the choreography, not just the endpoints.
Multi-step API workflows described with the Arazzo specification.
_Index
ARAZZOClawvisor — approve-scope-and-triage
Declare a read-scoped task, wait for the user to approve it, list and read messages through the gateway under scope, then complete the task. Every operationId is verified agains...
ARAZZOMCP Servers 1
Model Context Protocol servers expose these APIs directly to AI agents. We profile them because agent-native access is the fastest-growing way this provider's capabilities actually get used.
Model Context Protocol servers that expose these APIs to AI agents.
clawvisor-mcp.yml
MCP SERVEREvent Specifications 1
Not every API is request/response. AsyncAPI describes the event-driven and streaming side — the webhooks and channels — so the asynchronous half of the interface is documented the same way the synchronous half is.
AsyncAPI definitions for this provider's event-driven and streaming APIs.
Clawvisor Callbacks Webhooks
ASYNCAPISecurity Posture 2
Authentication, domain security, vulnerability disclosure, and trust-center signals — the evidence that a provider takes security seriously enough to document it. We profile it because you can't govern what you can't see.
Authentication, domain security, vulnerability disclosure, and trust-center signals.
Agentic Access 1
An x-agentic-access contract marks which operations are safe for an agent to run on its own and which need a human in the loop. It is the difference between an API an agent can use and one it can use safely.
Recommended x-agentic-access execution contracts for AI agents.
Resources
Every other property we hold for Clawvisor — documentation, portals, status pages, policies, and corporate surface — grouped by the job it does, following the integrator's arc from getting started to running in production.
Get Started 3
Portal, sign-up, and the first successful call
Documentation 2
Reference material describing how the API behaves
Agent Surfaces 5
MCP servers, agent skills, and machine-readable catalogs
Design & Contract 6
Pagination, idempotency, versioning, errors, and events
Build 3
SDKs, sample code, and the tooling you integrate with
Access & Security 2
Authentication, authorization, and security posture
Operate 1
Status, limits, changes, and where to get help
Commercial 3
Pricing, plans, and the legal terms of use
← All providers · Data indexed from github.com/api-evangelist/clawvisor · machine-readable index on apis.io