// MCP TOOL REFERENCE

AIR SDK TOOLS

5 tools from the AIR SDK MCP Server, categorised by risk level.

// ALL 5 AIR SDK TOOLS

READ 3 tools

Read browse_capabilities Step 1 of 3: Discover what actions can be automated on a website domain. Returns capabilities (search, logi... Read extract_content Extract text and structured sections from a file (PDF, DOCX, PPTX, XLSX, CSV, TXT, MD, HTML, EML). Returns ... Read extract_url Extract structured data from any URL. Returns title, description, content items, metadata, and diagnostics....

EXECUTE 2 tools

Execute execute_capability Step 2 of 3: Get execution guidance for a specific capability. Returns the optimal path: API fast-path, pre... Execute report_outcome REQUIRED: Report the outcome after executing ANY browser action via AIR. This is the final step of every br...

// RUNNING THIS SERVER

The managed route: connect AIR SDK through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y @arcede/air-sdk

// FAQ

How many tools does the AIR SDK MCP server have? +

The AIR SDK MCP server exposes 5 tools across 2 categories: Read, Execute.

How do I enforce policies on AIR SDK tools? +

Route the AIR SDK server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do AIR SDK tools fall into? +

AIR SDK tools are categorised as Read (3), Execute (2). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.