Smithery
Also known as: Smithery.ai
MCP registry and connection platform with managed OAuth, a Skills Registry, triggers and server publishing; acquired by Arcade.dev in August 2026.
Smithery is a registry and connection platform for Model Context Protocol servers. Its public registry lists thousands of MCP servers from many publishers, searchable by text or meaning, and a separate Skills Registry lists reusable prompt-based skills an agent can add with one command. Smithery Connect gives an agent authenticated access to those servers, or any MCP URL, through a REST API. Smithery maintains OAuth apps for popular integrations, refreshes tokens, stores credentials encrypted and write-only, and lets the customer list and call tools on each connection. Short-lived service tokens, in preview, scope an agent to particular namespaces, users and operations.
Publishers use Smithery to distribute their own servers, hosted by Smithery, proxied from their own URL or shipped as a local bundle, with analytics on tool calls and runtime logs. Triggers, also in preview, let a server deliver upstream events to the customer's webhook. Servers can run on the user's own machine through the CLI, or be exposed from it with Uplink.
Arcade.dev acquired Smithery in August 2026, according to Arcade's own announcement, and smithery.ai carries the notice while still selling Smithery under its own name. Pricing is a free Hobby plan with 50,000 RPCs a month, Pay as you Go at $10 a month including $10 of credit and then $0.10 per 1,000 RPCs, and a quoted Custom plan.
Vendor details
Canonical URL
https://smithery.ai
Category
Agent infrastructure
Subcategory
Tools and MCP
Funding status
Acquired by Arcade.dev in August 2026, per Arcade's own announcement; smithery.ai carries the notice and still sells Smithery under its own name.
Company status
acquired
Use cases & customers
Primary use cases
Target customers
Deployment options
Integrations
Thousands of MCP servers from many publishers sit in a searchable registry, reached through Smithery Connect's REST API or TypeScript SDK with managed OAuth, token refresh and write-only credential storage. Any custom MCP URL also works. The CLI installs servers locally into Claude Desktop, Cursor and other clients, and Smithery integrates with the Vercel AI SDK and the MCP SDK. Triggers deliver server events to the customer's webhook.
In practice
You are wiring tools into Claude or Cursor and cannot find the right MCP server. Smithery's registry lets you search thousands of servers and add one to your client through the CLI.
Your app's agent needs to call tools for each of your users without you building OAuth. Smithery Connect keeps a connection per user with managed OAuth and write-only credentials, and you call tools through its API.
You built an MCP server and want developers to find it. Publishing on Smithery gives it a listing page, an authentication prompt for users and analytics on tool calls.
Sources & related URLs
Agentic Index coverage score
7.5 / 14 capabilities · 54%
| Integrations & Tool Calling | Full |
|---|---|
|
Through the Smithery Connect REST API, an agent gets authenticated access to MCP servers. Smithery maintains OAuth apps for popular integrations, refreshes tokens automatically and stores credentials encrypted and write only. The agent lists and calls tools on each connection, whether the server comes from the registry of thousands of published servers or from any custom MCP URL. Most listed servers are published by third parties, while the connection, auth and credential layer is Smithery's own. Sourcesmithery.ai/docs/use/connectread 2026-09-22 |
|
| Workflow Orchestration | Not documented |
|
Sequencing, branching and retries live in the customer's own client or framework, such as the Vercel AI SDK that Smithery's guide uses. Smithery connects an agent to MCP servers and relays the tool calls it makes. It does not run the agent and names no workflow runtime of its own. Sourcesmithery.ai/docs/use/connectread 2026-09-22 |
|
| Knowledge Grounding & RAG | Not documented |
|
Semantic search runs over the public registry of servers and skills, not over the customer's own content. Servers that reach a customer's documents connect the agent to those systems, with no index of Smithery's own. Smithery names no ingestion, indexing, retrieval or RAG layer. Sourcesmithery.ai/docs/indexread 2026-09-22 |
|
| Human Oversight & Guardrails | Partial |
|
A connection stays in an auth_required or input_required state, and its tools are not called, until the user completes OAuth or supplies the missing configuration. Service tokens, from the Token Scoping feature in preview, limit an agent to named namespaces, resources and operations, such as read without execute. They are matched to a user's metadata and expire on a TTL. Smithery names no step where a person approves a specific agent action before it commits. Sourcesmithery.ai/docs/use/token-scopingread 2026-09-22 |
|
| Security, Identity & Governance | Partial |
|
Credentials are stored encrypted and write only, so they can be used but never read back. Organizations issue team API keys that only an admin role can create, list or revoke, and namespace ownership gates writes to servers and connections. Browser or mobile clients get short lived service tokens instead of the API key. No attestation or certification is published. Smithery offers documentation, a privacy policy and a status page, but no trust center, and it names no SSO or audit trail. Sourcesmithery.ai/docs/use/connectread 2026-09-22 |
|
| Observability & Auditability | Partial |
|
Activity is recorded on the server side. A publisher gets analytics on the tool calls made to its server, runtime logs grouped by invocation and release pipeline logs through the API. For a customer connecting an agent through Connect, Smithery names no step by step record of that agent's session, and no audit log, export or retention by plan. Sourcesmithery.ai/docs/api-reference/servers/list-runtime-logsread 2026-09-22 |
|
| Memory & State Persistence | Not documented |
|
Connections, their credentials and their MCP sessions stay alive for the customer, and Smithery says it is stateless for the customer's application. Smithery names no memory layer that keeps an agent's context across runs. Memory servers in the registry are other publishers' products. Sourcesmithery.ai/docs/use/connectread 2026-09-22 |
|
| Deployment & Data Residency | Full |
|
Tools can run where the customer chooses. Smithery hosts uploaded servers and proxies servers the customer hosts elsewhere by URL. The CLI or an MCPB bundle adds servers straight into a local client such as Claude Desktop or Cursor, so they run on the user's machine. Uplink exposes a server running locally as a Smithery connection without deploying it. No region selection is published for Smithery's own connection and credential service. Sourcesmithery.ai/docs/use/uplinkread 2026-09-22 |
|
| Prebuilt Agents, Templates & Packs | Full |
|
The Skills Registry, which Smithery runs, holds reusable prompt based skills that can be searched by text and semantic query and browsed as a catalog. One CLI command, smithery skill add, adds a skill to an agent such as Claude Code, so a customer adopts a ready made workflow instead of writing it. Sourcesmithery.ai/docs/concepts/cliread 2026-09-22 |
|
| Triggers & Channel Coverage | Full |
|
Triggers, in preview, let an MCP server surface events from its upstream service. The customer lists a connection's trigger types and subscribes through the Connect API with its own webhook URL and signing secret. When the upstream event fires, the server posts it straight to the customer's endpoint, so work starts without a person asking. Smithery warns that breaking changes are possible while triggers are in preview, and a trigger exists only where the server's publisher implements it. Sourcesmithery.ai/docs/build/triggersread 2026-09-22 |
|
| Model Flexibility & Routing | Full |
|
Whatever model and client the customer runs can use the tools. Smithery connections plug into any MCP client, the Vercel AI SDK and the MCP TypeScript SDK. The customer chooses the model and supplies its key, and Smithery names no model of its own. Sourcesmithery.ai/docs/integrations/vercel_ai_sdkread 2026-09-22 |
|
| APIs, SDKs & MCP Extensibility | Full |
|
A REST API at api.smithery.ai, with a published OpenAPI specification, covers servers, releases, connections, tools, triggers, skills, namespaces and tokens. A TypeScript SDK and a CLI sit alongside it. Smithery serves MCP as addressed endpoints for every connection, and publishers ship their own servers by URL, uploaded module or MCPB bundle. Sourcesmithery.ai/docs/use/connectread 2026-09-22 |
|
| Testing, Debugging & Optimization | Not documented |
|
When a server is published, Smithery scans it to extract its tools and metadata, shows a security status and runs a release pipeline with logs. These checks cover the server, not the customer's agent. Smithery names no way to test an agent against fixtures or datasets, score its output or gate a release on quality. Sourcesmithery.ai/docs/build/publishread 2026-09-22 |
|
| Browser & Computer Use | Not documented |
|
Agents can control browsers through Smithery by using the Browserbase server, which another company publishes in the registry. The capability and its documentation belong to that publisher. Smithery names no browser, desktop or computer control of its own. Sourcesmithery.ai/docs/indexread 2026-09-22 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Product updates
Smithery's connection management services shut down on October 31, 2026. Server URLs on run.tools and server.smithery.ai, the Smithery API, Connect and Toolbox, Smithery accounts and API keys, and the CLI and SDKs all stop working, with current CLI and SDK versions marked deprecated. What remains is a public directory of MCP servers, powered by Arcade.dev, that no longer proxies connections and lists each verified server's direct MCP URL.
Bears on: MCP / tool calling / API
View sourcePricing
Free Hobby (50K RPCs) · Pay as you Go $10/mo + $0.10 per 1K RPCs · Custom
Monthly plan fee converted to RPC credit, then metered per 1,000 RPCs
Included quota
Hobby: 50,000 RPCs a month, 3 namespaces, managed OAuth, persistent connections. Pay as you Go: $10 of RPC credit a month (100,000 RPCs) and 100 namespaces.
What is public
All self-serve tiers are priced with their allowances and the per-RPC rate; only Custom is quoted.
Billing mechanics
Start free on Hobby, move to Pay as you Go, where a $10 monthly fee becomes RPC credit and further RPCs bill at $0.10 per 1,000, or buy Custom on a quote.
Cost watchouts
Every RPC through a connection counts against the allowance, so a chatty agent can pass the $10 credit quickly and then pays $0.10 per 1,000. Uptime SLA and custom rate limits sit on the quoted Custom plan.
Variable cost rationale
Cost is metered per RPC after the $10 monthly credit, so it rises directly with agent tool traffic; the free Hobby allowance of 50,000 RPCs covers light use.
Overage / add-ons
$0.10 per 1,000 RPCs after the $10 monthly credit on Pay as you Go; custom on Custom.
Sales call required
Mixed (some tiers require a call)
Free / trial
Hobby free: 50,000 RPCs a month, 3 namespaces, managed OAuth
Lowest paid plan
Pay as you Go, $10 a month including $10 of RPC credit (100,000 RPCs), then $0.10 per 1,000 RPCs
Commercial notes
Acquired by Arcade.dev in August 2026; smithery.ai still sells Smithery under its own name with free sign-up.
Key ambiguities
The pricing page's own description still mentions a Pro plan that the plan table no longer shows. Custom plan terms are quoted. Smithery is now part of Arcade.dev, and no change to Smithery's plans has been announced.
Related vendors
- AgentOps — Agent observability and debugging platform: open source SDKs trace…
- AgentPhone — AgentPhone gives the AI agents a team builds their own US or…
- Agno — Python agent framework and AgentOS runtime (formerly Phidata) for…
- AIsa — Resource and payment gateway for AI agents, with one key to 110+…
- Albato — Albato is a no code integration platform that sells an embedded,…
- AlphaBitCore — AI control plane for regulated financial firms: one gateway enforces…
Alternatives to Smithery
The closest documented capability profiles to Smithery among agent infrastructure platforms tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- AIsa6.0 / 14A lighter documented profile than Smithery
- Arize AI9.0 / 14Adds documented Testing, Debugging & Optimization
- E2B8.0 / 14Adds documented Memory & State Persistence and Browser & Computer Use
- Metorial8.0 / 14Adds documented Testing, Debugging & Optimization
- Stacklok8.0 / 14Adds documented Testing, Debugging & Optimization
- Temporal Cortex8.0 / 14Adds documented Workflow Orchestration
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded