CALL THIS to record DECISIONS and CONVENTIONS. WHEN TO CALL: A. CONFLICT RESOLUTION — STOP IMMEDIATELY when any of these occur: - User says: "don't use X", "use Y instead", "prefer", "switch to". - During planning: user's request or your proposal differs from AI_README conventions. - During plann...
AI agents use update_ai_readme to create or update resources in Ai Readme — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ai Readme environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
operations | array | Yes | List of update operations to perform |
readmePath | string | Yes | Path to the AI_README.md file to update |
Parameters from the server's own tool schema.
This tool writes to configuration/documentation files (AI_README.md) to record project decisions and conventions. It modifies data reversibly—updates can be undone or corrected in subsequent calls. This fits the Write category (creates/modifies data reversibly).
From the tool's definition Tool description states 'CALL THIS to record DECISIONS and CONVENTIONS' and the name 'update_ai_readme' indicates modification of documentation files. The tool creates or modifies AI_README.md files reversibly.
Risk signalsAccepts raw HTML/template content (operations[].content)
Documented attack patterns abuse exactly the kind of access update_ai_readme gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ai Readme, and nothing reaches the server without passing your rules. This is the rule we recommend for update_ai_readme:
{
"version": "1",
"default": "deny",
"tools": {
"update_ai_readme": {
"limits": [
{
"counter": "update_ai_readme_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_ai_readme stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
CALL THIS to record DECISIONS and CONVENTIONS. WHEN TO CALL: A. CONFLICT RESOLUTION — STOP IMMEDIATELY when any of these occur: - User says: "don't use X", "use Y instead", "prefer", "switch to". - During planning: user's request or your proposal differs from AI_README conventions. - During planning: user approves a plan that contradicts AI_README. - User overrides a convention mid-task (even casually, e.g. 'just use X here'). - DO NOT continue planning or coding. Call update_ai_readme first, then resume. B. ARCHITECTURAL DECISIONS (during planning/implementation): - You chose a design pattern (e.g., repository pattern, factory, singleton). - You decided on API structure (REST paths, error format, response shape). - You established naming conventions (files, functions, variables). - You created new abstractions (utilities, hooks, services, types). - You set up error handling strategy or validation approach. - You introduced a new dependency or integration pattern. C. IMPLEMENTATION PATTERNS (after writing code): - You created a reusable pattern others should follow. - You established a file/folder structure for a new feature. - You made decisions that affect future development. D. MISSING / UNDOCUMENTED (during get_context or code review): - AI_README is missing a convention that is ALREADY USED in 2+ existing files. - A pattern exists in code but not in AI_README — record it so future code follows it. - Do NOT record one-off choices or speculative future patterns. RULE: If a decision will affect MORE THAN ONE FILE or FUTURE CODE → RECORD IT. WORKFLOW: 1. get_context (read current conventions). 2. Make decision or detect conflict. 3. update_ai_readme (record the decision). 4. Continue with implementation. Content Rules: - Extremely concise (< 400 tokens). - Only actionable conventions (tech, naming, patterns, infrastructure patterns, testing patterns). - NO explanations or examples. It is categorised as a Write tool in the Ai Readme MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
update_ai_readme accepts 2 parameters: operations, readmePath. Required: operations, readmePath. The full parameter table on this page comes from the server's own tool schema.
Register the Ai Readme MCP server in PolicyLayer and add a rule for update_ai_readme: 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 Ai Readme. Nothing to install.
update_ai_readme 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 update_ai_readme 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 update_ai_readme. 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.
update_ai_readme is provided by the Ai Readme MCP server (ai-readme-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Ai Readme, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
6 Ai Readme tools catalogued and risk-classified — across an index of 43,000+ MCP servers.