repo_lens_analyze
Analyze a repository and return a compact overview: file/dir counts, total bytes, language distribution, dependency manifests and a directory tree. Use this first when you need to understand an unfamiliar codebase (what languages it uses, what packages it depends on, how big it is). This tool per...
This record as markdown: /tools/1mper-labs-mcp-server/repo-lens-analyze.md
What repo_lens_analyze does on 1mper Labs
AI agents call repo_lens_analyze to retrieve information from 1mper Labs without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
dir | string | — | Directory to analyze. Defaults to the MCP server process working directory. |
json | boolean | — | Return the full RepoProfile as JSON instead of a text summary. |
Parameters from the server's own tool schema.
Why repo_lens_analyze is rated Low
Even though repo_lens_analyze only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Risk signalsAccepts file system path (dir)
Attacks that exploit this kind of access
The rule that runs repo_lens_analyze safely
PolicyLayer is an MCP gateway: it sits between your AI agents and 1mper Labs, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For repo_lens_analyze, this is the rule to start with:
repo_lens_analyze is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect 1mper Labs, apply this rule, and every repo_lens_analyze call is checked against it from then on.
Questions about repo_lens_analyze
Analyze a repository and return a compact overview: file/dir counts, total bytes, language distribution, dependency manifests and a directory tree. Use this first when you need to understand an unfamiliar codebase (what languages it uses, what packages it depends on, how big it is). This tool performs a fresh scan and never writes the cache, so it is side-effect free. Pass json=true for the full machine-readable profile; otherwise you get a human-readable summary. It is categorised as a Read tool in the 1mper Labs MCP Server, which means it retrieves data without modifying state.
repo_lens_analyze accepts 2 parameters: dir, json. The full parameter table on this page comes from the server's own tool schema.
Register the 1mper Labs MCP server in PolicyLayer and add a rule for repo_lens_analyze: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches 1mper Labs. Nothing to install.
repo_lens_analyze 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 repo_lens_analyze rule in your PolicyLayer 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 PolicyLayer policy for repo_lens_analyze. 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.
repo_lens_analyze is provided by the 1mper Labs MCP server (@1mper-labs/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on 1mper Labs, and thousands of servers like it.
This server
Across the catalogue