Manage graph version history (list, diff, restore)
AI agents use gid_history to create or update resources in GID MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your GID MCP Server environment.
While 'list' and 'diff' are read operations, the 'restore' capability allows reverting the graph to a prior state, which is a write operation that modifies the current graph representation. This is categorized as Write rather than Destructive because restoration is reversible (one can restore again to undo the restore).
From the tool's definition Tool description states 'Manage graph version history (list, diff, restore)' — the 'restore' operation modifies the graph state by reverting to a previous version, constituting a write operation that changes persisted data.
Attacks that exploit this kind of access
Manage graph version history (list, diff, restore). It is categorised as a Write tool in the GID MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the GID MCP Server MCP server in PolicyLayer and add a rule for gid_history: 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 GID MCP Server. Nothing to install.
gid_history 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 gid_history 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 gid_history. 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.
gid_history is provided by the GID MCP Server MCP server (potatouniverse/graph-indexed-development-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →