Discover existing features from codebase and generate specifications with speclinter-tasks directories
AI agents call speclinter_reverse_spec to retrieve information from SpecLinter MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs static analysis of a codebase to reverse-engineer or document existing features. This is a discovery and retrieval operation with no side effects—it does not execute code, modify the codebase, delete data, or trigger external operations. It generates output (specifications) based on input (codebase analysis), which is characteristic of Read category tools.
From the tool's definition Tool description states 'Discover existing features from codebase and generate specifications' — this is a read operation that analyzes and extracts information from existing code to produce documentation/specifications.
Documented attack patterns abuse exactly the kind of access speclinter_reverse_spec gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and SpecLinter MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for speclinter_reverse_spec:
{
"version": "1",
"default": "deny",
"tools": {
"speclinter_reverse_spec": {}
}
}speclinter_reverse_spec is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Discover existing features from codebase and generate specifications with speclinter-tasks directories. It is categorised as a Read tool in the SpecLinter MCP MCP Server, which means it retrieves data without modifying state.
Register the SpecLinter MCP server in PolicyLayer and add a rule for speclinter_reverse_spec: 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 SpecLinter MCP. Nothing to install.
speclinter_reverse_spec 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 speclinter_reverse_spec 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 speclinter_reverse_spec. 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.
speclinter_reverse_spec is provided by the SpecLinter MCP server (orangebread/speclinter-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 14 SpecLinter MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
14 SpecLinter MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.