// MCP TOOL REFERENCE

DEEPCONTEXT TOOLS

4 tools from the Deepcontext MCP Server, categorised by risk level.

READ TOOLS

get_indexing_status <tool> <purpose>Check if codebases are indexed and get their status information</purpose> <enhanced_features> <feature>Shows completion st... index_codebase <tool> <purpose>Prepares a codebase for intelligent search by creating a searchable index</purpose> <when_to_use> <scenario>Call this firs... search_codebase <tool> <purpose>Finds relevant code in an indexed codebase using natural language or keyword queries</purpose> <when_to_use> <scenario>Fin... 2/5

DESTRUCTIVE TOOLS

clear_index <tool> <purpose>Permanently removes all indexed data for a codebase</purpose> <when_to_use> <scenario>Clear stale data before reindexing a... 5/5

// FAQ

How many tools does the Deepcontext MCP server have? +

The Deepcontext MCP server exposes 4 tools across 2 categories: Read, Destructive.

How do I enforce policies on Deepcontext tools? +

Use Intercept, the open-source MCP proxy. Write YAML rules for each tool — rate limits, argument validation, or deny rules — then run Intercept in front of the Deepcontext server.

What risk categories do Deepcontext tools fall into? +

Deepcontext tools are categorised as Read (3), Destructive (1). Each category has a recommended default policy.

Enforce policies on Deepcontext

Open source. One binary. Zero dependencies.

npx -y @policylayer/intercept

github.com/policylayer/intercept →