Run on-demand entity resolution (deduplication) on the knowledge graph. Uses 3-tier matching: exact text → embedding similarity → LLM verification. Merges duplicate entities by transferring relationships and ABOUT edges to the canonical entity.
AI agents use resolve_entities to create or update resources in CodeGraph — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your CodeGraph environment.
The tool modifies the knowledge graph by merging entities and transferring relationships, which constitutes Write rather than Read. It does not permanently delete data (making it less severe than Destructive), but it does alter graph structure through entity consolidation.
From the tool's definition 'Merges duplicate entities by transferring relationships and ABOUT edges to the canonical entity' indicates modification of knowledge graph structure through deduplication operations that irreversibly consolidate data.
Documented attack patterns abuse exactly the kind of access resolve_entities gives an agent:
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 resolve_entities:
{
"version": "1",
"default": "deny",
"tools": {
"resolve_entities": {
"limits": [
{
"counter": "resolve_entities_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}resolve_entities 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.
Run on-demand entity resolution (deduplication) on the knowledge graph. Uses 3-tier matching: exact text → embedding similarity → LLM verification. Merges duplicate entities by transferring relationships and ABOUT edges to the canonical entity. 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.
Register the CodeGraph MCP server in PolicyLayer and add a rule for resolve_entities: 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.
resolve_entities 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 resolve_entities 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 resolve_entities. 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.
resolve_entities 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.
Start from CodeGraph, 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.
18 CodeGraph tools catalogued and risk-classified — across an index of 43,000+ MCP servers.