Add new observations to existing entities in the knowledge graph
AI agents use add_observations to create or update resources in Obsidian Memory MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Obsidian Memory MCP environment.
An AI agent can call add_observations faster than any human can review — one bad instruction and it creates or modifies resources in Obsidian Memory MCP by the hundred, each call as confident as the last.
Documented attack patterns abuse exactly the kind of access add_observations gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Obsidian Memory MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for add_observations:
{
"version": "1",
"default": "deny",
"tools": {
"add_observations": {
"limits": [
{
"counter": "add_observations_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}add_observations 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.
Add new observations to existing entities in the knowledge graph. It is categorised as a Write tool in the Obsidian Memory MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Obsidian Memory MCP server in PolicyLayer and add a rule for add_observations: 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 Obsidian Memory MCP. Nothing to install.
add_observations 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 add_observations 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 add_observations. 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.
add_observations is provided by the Obsidian Memory MCP server (yunaga224/obsidian-memory-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 9 Obsidian Memory MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
9 Obsidian Memory MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.