<tool> <purpose>Check if codebases are indexed and get their status information</purpose> <enhanced_features> <feature>Shows completion statistics for finished indexing (success rates, processing time, performance metrics)</feature> <feature>Displays batch processing details (success...
Part of the Deepcontext MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents call get_indexing_status to retrieve information from Deepcontext without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though get_indexing_status only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
tools:
get_indexing_status:
rules:
- action: allowSee the full Deepcontext policy for all 4 tools.
Agents calling read-class tools like get_indexing_status have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Read risk category across the catalogue. The same policy patterns (rate-limit, allow) apply to each.
<tool> <purpose>Check if codebases are indexed and get their status information</purpose> <enhanced_features> <feature>Shows completion statistics for finished indexing (success rates, processing time, performance metrics)</feature> <feature>Displays batch processing details (successful/skipped batches)</feature> <feature>References log files for detailed debugging</feature> </enhanced_features> <when_to_use> <scenario>Before indexing to check if already done</scenario> <scenario>After indexing to see completion statistics and success rates</scenario> <scenario>Debug why search returned no results</scenario> <scenario>Confirm indexing completed successfully</scenario> <scenario>Get overview of all indexed codebases</scenario> </when_to_use> <parameters> <parameter name="codebase_path" required="false"> <type>string</type> <description>ABSOLUTE path to specific codebase to check</description> <examples> <valid>/Users/name/project</valid> <valid>/home/user/code/repo</valid> <invalid>.</invalid> <invalid>../project</invalid> <invalid>relative/path</invalid> </examples> <validation>Must be absolute path starting with / (Unix) or C:\ (Windows)</validation> <optional_behavior>Omit to get status of all indexed codebases</optional_behavior> </parameter> </parameters> <returns>Enhanced indexing status with completion statistics when available</returns> </tool>. It is categorised as a Read tool in the Deepcontext MCP Server, which means it retrieves data without modifying state.
Add a rule in your Intercept YAML policy under the tools section for get_indexing_status. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Deepcontext MCP server.
get_indexing_status is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_indexing_status rule in your Intercept policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the Intercept policy for get_indexing_status. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_indexing_status is provided by the Deepcontext MCP server (@wildcard-ai/deepcontext). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept