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 wh...
Risk signalsAccepts file system path (file)
Part of the Agda server.
Free to start. No card required.
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. PolicyLayer'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.
{
"version": "1",
"default": "deny",
"tools": {
"agda_apply_edit": {
"limits": [
{
"counter": "agda_apply_edit_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full Agda policy for all 72 tools.
These attack patterns abuse exactly the kind of access agda_apply_edit gives an agent. Each links to the full case and the policy that stops it:
Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
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.
Register the Agda MCP server in PolicyLayer and add a rule for agda_apply_edit: 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 Agda. Nothing to install.
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 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 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). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 72 Agda tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.