AI agents use writeRaw to create or update resources in ThinkMem — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your ThinkMem environment.
The tool writes or modifies data in raw memory storage with overwrite or append capabilities. This is a Write operation because: (1) it creates/modifies data, (2) the operation is reversible (can be overwritten or deleted via sibling tools like deleteRawLines or deleteMemory), and (3) it does not execute arbitrary code, delete irreversibly, or move money.
From the tool's definition Tool name 'writeRaw' and description '向RawMemory写入文本内容，支持覆盖模式或追加模式' (Write text content to RawMemory, supporting overwrite or append mode) indicates creation or modification of data in a reversible manner.
Documented attack patterns abuse exactly the kind of access writeRaw gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ThinkMem, and nothing reaches the server without passing your rules. This is the rule we recommend for writeRaw:
{
"version": "1",
"default": "deny",
"tools": {
"writeRaw": {
"limits": [
{
"counter": "writeraw_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}writeRaw 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.
向RawMemory写入文本内容，支持覆盖模式或追加模式。. It is categorised as a Write tool in the ThinkMem MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the ThinkMem MCP server in PolicyLayer and add a rule for writeRaw: 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 ThinkMem. Nothing to install.
writeRaw 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 writeRaw 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 writeRaw. 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.
writeRaw is provided by the ThinkMem MCP server (rickonono3/thinkmem). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ThinkMem, 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.
28 ThinkMem tools catalogued and risk-classified — across an index of 43,000+ MCP servers.