Create or update a note under a key. Returns the note id.
AI agents use index-upsert to create or update resources in MCP Index Notes — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Index Notes environment.
index-upsert performs create and update operations on notes stored in the SQLite-backed index. These are Write-category actions because they are reversible (notes can be edited again or deleted). The severity is medium because uncontrolled writes could introduce incorrect data, pollution of the knowledge graph, or storage exhaustion, but the effects remain reversible.
From the tool's definition Tool description states 'Create or update a note' — these are reversible write operations that modify data in the note index.
Attacks that exploit this kind of access
Create or update a note under a key. Returns the note id. It is categorised as a Write tool in the MCP Index Notes MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Index Notes MCP server in PolicyLayer and add a rule for index-upsert: 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 MCP Index Notes. Nothing to install.
index-upsert 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 index-upsert 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 index-upsert. 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.
index-upsert is provided by the MCP Index Notes MCP server (vjsr007/mcp-index-notes). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →