project_context
Fetch the repo's agent-guidance files (CLAUDE.md, AGENTS.md, AI_ARCH.md, REMOTE_WORKER.md) plus the project's init.md. Every result is prefixed with a stale-docs warning. Use this at the start of a task for context, but remember: the docs may be out of date — always grep the code to verify claims...
This record as markdown: /tools/io-github-kivanccakmak-yaver/project-context.md
What project_context does on Yaver
AI agents call project_context to retrieve information from Yaver without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
workDir | string | — | Project root (defaults to the agent's active work-dir). |
Parameters from the server's own tool schema.
Why project_context is rated Low
The tool only retrieves and returns documentation files from the repository. It performs a read-only operation with no side effects — no data is created, modified, deleted, or executed. The advisory to 'grep the code to verify claims' further confirms this is a passive information-fetching tool.
From the tool's definition Fetch the repo's agent-guidance files (CLAUDE.md, AGENTS.md, AI_ARCH.md, REMOTE_WORKER.md) plus the project's init.md
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs project_context safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Yaver, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For project_context, this is the rule to start with:
project_context is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Yaver, apply this rule, and every project_context call is checked against it from then on.
Questions about project_context
Fetch the repo's agent-guidance files (CLAUDE.md, AGENTS.md, AI_ARCH.md, REMOTE_WORKER.md) plus the project's init.md. Every result is prefixed with a stale-docs warning. Use this at the start of a task for context, but remember: the docs may be out of date — always grep the code to verify claims before acting on them. It is categorised as a Read tool in the Yaver MCP Server, which means it retrieves data without modifying state.
project_context accepts 1 parameter: workDir. The full parameter table on this page comes from the server's own tool schema.
Register the Yaver MCP server in PolicyLayer and add a rule for project_context: 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 Yaver. Nothing to install.
project_context 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 project_context 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 project_context. 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.
project_context is provided by the Yaver MCP server (yaver-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Yaver, and thousands of servers like it.
This server
Across the catalogue