add

THE RISK

Medium Risk

Why add needs a policy

The 'add' tool modifies the knowledge graph by ingesting new content, making it a Write operation. It is not Destructive because ingestion is reversible (data can be removed or updated). Severity is medium because misuse could pollute the knowledge graph with malicious content, but the impact is limited to the graph itself without executing arbitrary code or affecting external systems.

From the tool's definition Tool description states 'Ingest any content into the knowledge graph' which creates or adds data to a persistent storage system. The tool accepts multiple file types (PDF, DOCX, HTML, CSV) for import.

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

POLICY

How to control add

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

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "add": {
      "limits": [
        {
          "counter": "add_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

add 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 CodeGraph — 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 CodeGraph tools

Destructive decay_and_prune Run temporal memory maintenance: decay relevance scores for old entities and optionally pr Execute trigger_reindex Trigger a reindex of the codebase. Supports incremental (changed files only) or full mode. Execute query_graph Run a raw Cypher query against the code graph. Use with caution - read-only queries only. Write ingest_conversation Ingest a multi-turn conversation into the knowledge graph. Runs the full episodic pipeline Write store_entity Store an entity in the knowledge graph. Deduplicates by text+type — if an entity with the Write store_fact Extract entities and relationships from natural language text using an LLM, then store the Write store_relationship Store a relationship between two entities in the knowledge graph. Entities are referenced Write resolve_entities Run on-demand entity resolution (deduplication) on the knowledge graph. Uses 3-tier matchi

All 18 CodeGraph 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

What does the add tool do? +

Ingest any content into the knowledge graph. Accepts file paths (PDF, DOCX, HTML, CSV,. It is categorised as a Write tool in the CodeGraph 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? +

Register the CodeGraph MCP server in PolicyLayer and add a rule for add: 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 CodeGraph. Nothing to install.

What risk level is add? +

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

Can I rate-limit add? +

Yes. Add a rate_limit block to the add 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 completely? +

Set action: deny in the PolicyLayer policy for add. 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? +

add is provided by the CodeGraph MCP server (phoenixrr2113/codebase-graph). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every CodeGraph tool call.

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

CHECK YOUR STACK →