surf-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FARA_MODEL_IDS | No | Fara model IDs to use | |
| GOOGLE_API_KEY | No | Google API key for Gemini | |
| OPENAI_API_KEY | No | OpenAI-compatible API key | |
| SURF_LLM_MODEL | No | LLM model identifier (e.g., microsoft_fara-7b, gemini-2.0-flash) | |
| OPENAI_BASE_URL | No | OpenAI-compatible base URL | |
| LMSTUDIO_SERVERS | No | Multi-server LM Studio endpoints for visual grounding | |
| FARA_MAX_FAILURES | No | Max failures per action | 2 |
| SURF_LLM_PROVIDER | No | LLM provider (e.g., gemini) | |
| SURF_MAX_SESSIONS | No | Maximum number of concurrent sessions | 10 |
| FARA_PROBE_TIMEOUT | No | Probe timeout for server discovery | 2.0 |
| FARA_MIN_CONFIDENCE | No | Minimum confidence threshold | 0.7 |
| FARA_MAX_AGENT_STEPS | No | Maximum steps in autonomous mode | 20 |
| SURF_BROWSER_HEADLESS | No | Run browser in headless mode | true |
| FARA_CONFIDENCE_RETRIES | No | Number of retries on low confidence | 2 |
| SURF_BROWSER_VIEWPORT_WIDTH | No | Viewport width in pixels | 1920 |
| SURF_BROWSER_VIEWPORT_HEIGHT | No | Viewport height in pixels | 1080 |
| SURF_SESSION_TIMEOUT_SECONDS | No | Session timeout in seconds | 3600 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| session_createB | Create a new navigator session with one or more drivers |
| session_destroyA | Destroy a session and cleanup all its drivers |
| session_listB | List all active sessions |
| gotoC | Navigate to a location (path for filesystem, URL for browser) |
| currentC | Get current location for a driver |
| backC | Navigate back in history |
| forwardC | Navigate forward in history |
| historyC | Get navigation history for a driver |
| listA | List contents at current location (directory entries for filesystem, links for browser) |
| readA | Read content (file for filesystem, page text for browser) |
| snapshotC | Capture current state (JSON for filesystem, PNG screenshot for browser) |
| locateB | Locate UI element by natural language description (browser driver only) |
| clickC | Click UI element by description (browser driver only) |
| typeB | Type text into UI element by description (browser driver only) |
| scrollB | Scroll page (browser driver only) |
| waitA | Wait for element or delay (browser driver only) |
| actA | Execute a goal using direct Fara visual grounding. Fara decides what action to take (click, type, scroll, etc.) based on the goal and screenshot. |
| act_autonomousB | Execute a goal autonomously with multiple steps. Fara loops until task completion (terminate action) or max steps reached. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/shanevcantwell/surf-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server