Create or update a tiddler with the specified content and fields
AI agents use write_tiddler to create or update resources in Tiddly MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Tiddly MCP environment.
write_tiddler creates or updates tiddlers (wiki entries) but does not delete or permanently destroy data. The operation is reversible through subsequent writes or deletes. Severity is medium because an AI agent could modify important wiki content, potentially causing disruption, but the effects are not irreversible and the scope is limited to single tiddler modifications rather than bulk operations.
From the tool's definition Tool explicitly performs 'Create or update a tiddler' - reversible modification of data in TiddlyWiki. This is a write operation that modifies the wiki's content.
Documented attack patterns abuse exactly the kind of access write_tiddler gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Tiddly MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for write_tiddler:
{
"version": "1",
"default": "deny",
"tools": {
"write_tiddler": {
"limits": [
{
"counter": "write_tiddler_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}write_tiddler 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.
Create or update a tiddler with the specified content and fields. It is categorised as a Write tool in the Tiddly MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Tiddly MCP server in PolicyLayer and add a rule for write_tiddler: 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 Tiddly MCP. Nothing to install.
write_tiddler 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 write_tiddler 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 write_tiddler. 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.
write_tiddler is provided by the Tiddly MCP server (rryan/tiddly-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Tiddly MCP, 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.
5 Tiddly MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.