New Your team’s decisions, in one playbook every coding agent works from. Never answer your agent twice

get_graph_diff

[MAINTENANCE] Read-only: compare the latest code-graph snapshots of two sessions — returns delta in node_count, hotspot_count, and file_churn. Use snapshot_graph_metrics first to record each session's current state.

SERVERMeridian SOURCE@meridianmcp/mcp
Low RISK CLASS
Category Read
Parameters 22 required
Recommended Allowedsee the rule below
Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-ajc3xc-meridian/get-graph-diff.md

What get_graph_diff does on Meridian

AI agents call get_graph_diff to retrieve information from Meridian without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

ParameterTypeRequiredDescription
session_a string Yes First session ID.
session_b string Yes Second session ID to compare against session_a.

Parameters from the server's own tool schema.

Why get_graph_diff is rated Low

get_graph_diff retrieves and compares existing code-graph data between sessions, returning only derived metrics (deltas). It performs no writes, deletions, or external operations. The [MAINTENANCE] tag and explicit read-only designation confirm this is a non-mutating query tool. Low severity because misuse would only expose code metrics without capability to modify or execute anything.

From the tool's definition Tool description explicitly states 'Read-only: compare the latest code-graph snapshots' and 'returns delta in node_count, hotspot_count, and file_churn' — a pure retrieval and comparison operation with no side effects.

Questions about get_graph_diff

What does the get_graph_diff tool do? +

[MAINTENANCE] Read-only: compare the latest code-graph snapshots of two sessions — returns delta in node_count, hotspot_count, and file_churn. Use snapshot_graph_metrics first to record each session's current state. It is categorised as a Read tool in the Meridian MCP Server, which means it retrieves data without modifying state.

What parameters does get_graph_diff accept? +

get_graph_diff accepts 2 parameters: session_a, session_b. Required: session_a, session_b. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on get_graph_diff? +

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

What risk level is get_graph_diff? +

get_graph_diff is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get_graph_diff? +

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

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

get_graph_diff is provided by the Meridian MCP server (@meridianmcp/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

More on Meridian, and thousands of servers like it.

// THE MCP REGISTRY

PolicyLayer tracks 44,603 MCP servers and 515,000+ tools.

Every server has a live record: who publishes it, whether it answers without auth, its risk grade, every tool classified, the recommended policy. This page is one line of Meridian's. Pull the full record:

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.