Save research to collective memory. Call directly BEFORE responding to the user, after any live research (web search, URL fetch, context7). Content is PUBLIC, consumed by LLMs worldwide. ALWAYS English. Dense structured notes — no tutorials. NEVER include: project/repo/company names, internal URL...
AI agents use save to create or update resources in Wellread — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Wellread environment.
This tool creates and persists data to a shared research cache accessible by multiple AI agents and users globally. While the data saved is intended to be non-sensitive research content, the tool's core function is to write/store information reversibly. It is not Read (it modifies state), not Execute/Destructive (no code execution or irreversible deletion), not Financial.
From the tool's definition Tool description states 'Save research to collective memory' and 'Content is PUBLIC, consumed by LLMs worldwide', indicating it creates and stores data that persists across sessions and users.
Documented attack patterns abuse exactly the kind of access save gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Wellread, and nothing reaches the server without passing your rules. This is the rule we recommend for save:
{
"version": "1",
"default": "deny",
"tools": {
"save": {
"limits": [
{
"counter": "save_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}save 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.
Save research to collective memory. Call directly BEFORE responding to the user, after any live research (web search, URL fetch, context7). Content is PUBLIC, consumed by LLMs worldwide. ALWAYS English. Dense structured notes — no tutorials. NEVER include: project/repo/company names, internal URLs, file paths, credentials, business logic. Set volatility: timeless (established facts), stable (mature frameworks), evolving (active libraries), volatile (betas/pre-releases). search_surface MUST use this format: [TOPIC]: Semantic caching for LLM API calls [COVERS]: hit rates, cost reduction, cache invalidation [TECHNOLOGIES]: Next.js 15, React 19, Auth.js v5 [RELATED]: authentication, server components, middleware [SOLVES]: Setting up authentication in Next.js App Router. It is categorised as a Write tool in the Wellread MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Wellread MCP server in PolicyLayer and add a rule for save: 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 Wellread. Nothing to install.
save 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 save 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 save. 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.
save is provided by the Wellread MCP server (mnlt/wellread). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Wellread, 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.
3 Wellread tools catalogued and risk-classified — across an index of 43,000+ MCP servers.