// MCP TOOL REFERENCE

ALTERLAB TOOLS

23 tools from the Alterlab MCP Server, categorised by risk level.

// ALL 23 ALTERLAB TOOLS

READ 17 tools

Read alterlab_batch alterlab_batch Read alterlab_batch_status alterlab_batch_status Read alterlab_check_balance alterlab_check_balance Read alterlab_crawl alterlab_crawl Read alterlab_crawl_status alterlab_crawl_status Read alterlab_estimate_cost alterlab_estimate_cost Read alterlab_extract alterlab_extract Read alterlab_get_session alterlab_get_session Read alterlab_list_beta_features alterlab_list_beta_features Read alterlab_list_my_beta_features alterlab_list_my_beta_features Read alterlab_list_sessions alterlab_list_sessions Read alterlab_map alterlab_map Read alterlab_refresh_session alterlab_refresh_session Read alterlab_scrape alterlab_scrape Read alterlab_screenshot alterlab_screenshot Read alterlab_search alterlab_search Read alterlab_validate_session alterlab_validate_session

WRITE 4 tools

Write alterlab_create_session alterlab_create_session Write alterlab_disable_beta_feature alterlab_disable_beta_feature Write alterlab_enable_beta_feature alterlab_enable_beta_feature Write alterlab_update_session alterlab_update_session

DESTRUCTIVE 2 tools

Destructive alterlab_crawl_cancel alterlab_crawl_cancel Destructive alterlab_delete_session alterlab_delete_session

// RUNNING THIS SERVER

The managed route: connect Alterlab 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 alterlab-mcp-server

// FAQ

How many tools does the Alterlab MCP server have? +

The Alterlab MCP server exposes 23 tools across 3 categories: Read, Write, Destructive.

How do I enforce policies on Alterlab tools? +

Route the Alterlab 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 Alterlab tools fall into? +

Alterlab tools are categorised as Read (17), Write (4), Destructive (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.