add_observations

THE RISK

Medium Risk

Why add_observations needs a policy

This tool creates or modifies data (observations attached to entities) in a reversible manner. While it adds information to a knowledge graph, the modification is not permanent—observations can be removed. This places it in the Write category rather than Destructive.

From the tool's definition Tool name is 'add_observations' and description states it will 'ADD new factual observations to existing entities', indicating creation/modification of data. The operation is reversible via the sibling 'delete_observations' tool.

Documented attack patterns abuse exactly the kind of access add_observations gives an agent:

POLICY

How to control add_observations

PolicyLayer is an MCP gateway — it sits between your AI agents and KnowledgeGraph MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for add_observations:

policy.json

{
  "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.

Create a free account and register KnowledgeGraph MCP Server — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More KnowledgeGraph MCP Server tools

Destructive delete_entities Permanently DELETE entities and all their RELATIONSHIPS. This action is irreversible and c Destructive delete_observations DELETE specific OBSERVATIONS from entities while preserving the entity, its relationships, Destructive delete_relations DELETE specific RELATIONSHIPS between entities while preserving both entities. Use for upd Write remove_tags REMOVE specific TAGS from existing entities to maintain accurate categorization. Use for s Write add_tags ADD categorical TAGS to existing entities for filtering and organization. Tags are case-se Write create_entities CREATE new entities with OBSERVATIONS and optional tags. MANDATORY: If creating multiple e Write create_relations CREATE directional RELATIONSHIPS between existing entities. Both source and target entitie Read read_graph RETRIEVE the complete KNOWLEDGE GRAPH with all entities and relationships for a project. R

All 11 KnowledgeGraph MCP Server tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about add_observations

What does the add_observations tool do? +

ADD new factual observations to existing entities. Requires exact entity names that exist in the knowledge graph. Use search_knowledge first to verify entity existence. It is categorised as a Write tool in the KnowledgeGraph MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on add_observations? +

Register the KnowledgeGraph MCP Server 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 KnowledgeGraph MCP Server. Nothing to install.

What risk level is add_observations? +

add_observations is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit add_observations? +

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.

How do I block add_observations completely? +

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.

What MCP server provides add_observations? +

add_observations is provided by the KnowledgeGraph MCP Server MCP server (n-r-w/knowledgegraph-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every KnowledgeGraph MCP Server tool call.

Start from KnowledgeGraph MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →