Apply a targeted text substitution to an Agda file and reload it. For edits that aren't goal actions — adding imports, renaming symbols, fixing typos. oldText must match exactly once unless `occurrence` is provided. Auto-reloads the file after writing so the Agda session stays in sync. Runs even ...
Accepts file system path (file)
Part of the Agda MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents use agda_apply_edit to create or modify resources in Agda. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call agda_apply_edit repeatedly, creating or modifying resources faster than any human could review. Intercept's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Agda.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
tools:
agda_apply_edit:
rules:
- action: allow
rate_limit:
max: 30
window: 60See the full Agda policy for all 71 tools.
Agents calling write-class tools like agda_apply_edit have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Write risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.
Apply a targeted text substitution to an Agda file and reload it. For edits that aren't goal actions — adding imports, renaming symbols, fixing typos. oldText must match exactly once unless `occurrence` is provided. Auto-reloads the file after writing so the Agda session stays in sync. Runs even when the session is in a type-error state, since the whole point is to repair that state. Restricted to Agda source files (.agda, .lagda, .lagda.{md,rst,tex,org,typ}) and to source files ≤ 512 KiB; refuses symlink targets and out-of-sandbox paths.. It is categorised as a Write tool in the Agda MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Add a rule in your Intercept YAML policy under the tools section for agda_apply_edit. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Agda MCP server.
agda_apply_edit is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the agda_apply_edit 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 agda_apply_edit. 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.
agda_apply_edit is provided by the Agda MCP server (agda-mcp-server). 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