Stacklok
Stacklok is an open-source company building trust and governance infrastructure for AI agents and the Model Context Protocol (MCP). Its flagship open-source project, ToolHive (Apache 2.0), runs, secures, and governs MCP servers and agent skills across desktop, CLI, and Kubernetes, while the Stacklok Enterprise Platform and AI Gateway add centralized policy (Cedar/RBAC), OIDC authorization, LLM spend control, and a governed registry. Stacklok exposes two OpenAPI 3.1 surfaces — the ToolHive control API (thv serve, /api/v1beta) and the ToolHive Registry Server API (MCP Registry API v0.1 plus a /v1 admin API) — plus the thv CLI. Founded by Craig McLuckie and Luke Hinds; backed by Accel and Bain Capital Ventures.
Limited machine-readable signal and partial portal coverage — documentation a human can read, but little a machine or agent can consume without scraping.
API Evangelist profiles Stacklok the way a machine reads it — 17 machine-readable artifacts across 13 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 — Stacklok scores 43.5/100 (thin), with a separate agent-readiness read of 65/100 (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 Stacklok
Each block below is one kind of artifact we hold for Stacklok. 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 13
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.
ToolHive Registry API
The ToolHive Registry Server API for discovering, governing, and controlling access to MCP servers and agent skills — MCP Registry API v0.1 (read) plus a /v1 admin API. OpenAPI ...
Stacklok clients API
The clients API from Stacklok — 5 operation(s) for clients.
Stacklok discovery API
The discovery API from Stacklok — 1 operation(s) for discovery.
Stacklok groups API
The groups API from Stacklok — 2 operation(s) for groups.
Stacklok logs API
The logs API from Stacklok — 2 operation(s) for logs.
Stacklok registry-servers API
The registry-servers API from Stacklok — 2 operation(s) for registry-servers.
Stacklok registry-skills API
The registry-skills API from Stacklok — 2 operation(s) for registry-skills.
Stacklok secrets API
The secrets API from Stacklok — 4 operation(s) for secrets.
Stacklok skills API
The skills API from Stacklok — 12 operation(s) for skills.
Stacklok system API
The system API from Stacklok — 3 operation(s) for system.
Stacklok v1 API
The v1 API from Stacklok — 10 operation(s) for v1.
Stacklok version API
The version API from Stacklok — 1 operation(s) for version.
Stacklok workloads API
The workloads API from Stacklok — 13 operation(s) for workloads.
Scroll within the panel for all 13 ·
MCP 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.
stacklok-mcp.yml
MCP SERVERSecurity 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 Stacklok — 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 2
Portal, sign-up, and the first successful call
Documentation 2
Reference material describing how the API behaves
Agent Surfaces 4
MCP servers, agent skills, and machine-readable catalogs
Design & Contract 5
Pagination, idempotency, versioning, errors, and events
Build 5
SDKs, sample code, and the tooling you integrate with
Access & Security 2
Authentication, authorization, and security posture
Operate 2
Status, limits, changes, and where to get help
Commercial 1
Pricing, plans, and the legal terms of use
Company 2
The organization behind the API
← All providers · Data indexed from github.com/api-evangelist/stacklok · machine-readable index on apis.io