Analyze source-code call graphs (tree-sitter + Prolog). Absolute paths only. Languages: TypeScript, JavaScript, Python, Go, Rust, Clojure. ANALYSES: summary overview counts callers who calls target (needs target) callees what target calls (needs target) reachability can from reach to (needs from,...
AI agents call chiasmus_graph to retrieve information from Chiasmus without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
chiasmus_graph is a static analysis tool that examines and reports on code structure and call dependencies. It performs queries (summary, callers, callees, reachability, path-finding, impact analysis, dead-code detection, cycle detection) but does not execute code, modify files, delete data, or trigger external operations. The 'Absolute paths only' constraint indicates file system queries, not modifications.
From the tool's definition Tool performs static analysis of source-code call graphs using tree-sitter and Prolog. Descriptions use analysis verbs: 'Analyze', 'overview counts', 'who calls', 'what calls', 'can reach', 'shortest chain', 'transitive callers', 'unreachable functions',…
Documented attack patterns abuse exactly the kind of access chiasmus_graph gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Chiasmus, and nothing reaches the server without passing your rules. This is the rule we recommend for chiasmus_graph:
{
"version": "1",
"default": "deny",
"tools": {
"chiasmus_graph": {}
}
}chiasmus_graph is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Analyze source-code call graphs (tree-sitter + Prolog). Absolute paths only. Languages: TypeScript, JavaScript, Python, Go, Rust, Clojure. ANALYSES: summary overview counts callers who calls target (needs target) callees what target calls (needs target) reachability can from reach to (needs from, to) path shortest chain from→to (needs from, to) impact transitive callers of target (needs target) dead-code unreachable functions (methods excluded) cycles circular call dependencies layer-violation calls that skip layers (handlers→db bypassing services) communities Louvain clusters with cohesion scores hubs top-degree nodes bridges top betweenness — connect otherwise-separate subgraphs surprises cross-community + peripheral→hub edges diff current graph vs saved snapshot (needs against) entry-points zero-in-degree exports — seed dead-code facts raw Prolog for chiasmus_verify. It is categorised as a Read tool in the Chiasmus MCP Server, which means it retrieves data without modifying state.
Register the Chiasmus MCP server in PolicyLayer and add a rule for chiasmus_graph: 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 Chiasmus. Nothing to install.
chiasmus_graph is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the chiasmus_graph 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 chiasmus_graph. 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.
chiasmus_graph is provided by the Chiasmus MCP server (yogthos/chiasmus). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 11 Chiasmus tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
11 Chiasmus tools catalogued and risk-classified — across an index of 42,500+ MCP servers.