関連プロジェクトを一時的に追加します(セッション中のみ有効)。対象プロジェクトの起動済みsearch-docsサーバURLを指定してください。
AI agents use add_related_project to create or update resources in Search Docs — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Search Docs environment.
The tool creates or modifies session-level configuration by adding project references. It is reversible (session-scoped, temporary), has no destructive capability, and poses minimal risk—a user could add incorrect project URLs at worst, causing search queries to reference wrong sources.
From the tool's definition Tool description states it 'adds' related projects (一時的に追加 = temporarily adds) to the session. This is a create/modify operation that persists data within the session scope.
Attacks that exploit this kind of access
関連プロジェクトを一時的に追加します(セッション中のみ有効)。対象プロジェクトの起動済みsearch-docsサーバURLを指定してください。. It is categorised as a Write tool in the Search Docs MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Search Docs MCP server in PolicyLayer and add a rule for add_related_project: 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 Search Docs. Nothing to install.
add_related_project 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 add_related_project 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 add_related_project. 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.
add_related_project is provided by the Search Docs MCP server (otolab/search-docs). 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 →