Medium Risk

cairn_write_history

Write a new history entry directly to .cairn/history/ — no staging, no gate. Use this after completing a task that produced a recordable event: significant decision, rejected direction, accepted debt, or tried-and-abandoned approach. The 'rejected' field is the most critical — it records what alt...

High parameter count (12 properties)

Part of the Cairn MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.

AI agents use cairn_write_history to create or modify resources in Cairn. 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 cairn_write_history 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 Cairn.

Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.

cairn.yaml
tools:
  cairn_write_history:
    rules:
      - action: allow
        rate_limit:
          max: 30
          window: 60

See the full Cairn policy for all 6 tools.

Tool Name cairn_write_history
Category Write
MCP Server Cairn MCP Server
Risk Level Medium

Agents calling write-class tools like cairn_write_history have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

Other tools in the Write risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.

What does the cairn_write_history tool do? +

Write a new history entry directly to .cairn/history/ — no staging, no gate. Use this after completing a task that produced a recordable event: significant decision, rejected direction, accepted debt, or tried-and-abandoned approach. The 'rejected' field is the most critical — it records what alternatives were considered and not chosen, preventing AI from re-proposing already-evaluated paths.. It is categorised as a Write tool in the Cairn MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on cairn_write_history? +

Add a rule in your Intercept YAML policy under the tools section for cairn_write_history. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Cairn MCP server.

What risk level is cairn_write_history? +

cairn_write_history is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit cairn_write_history? +

Yes. Add a rate_limit block to the cairn_write_history 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.

How do I block cairn_write_history completely? +

Set action: deny in the Intercept policy for cairn_write_history. 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.

What MCP server provides cairn_write_history? +

cairn_write_history is provided by the Cairn MCP server (cairn-mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Let agents act without letting them run wild.

Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.