Low Risk

bear_context_fetch

Load the full content of specific files from the context library. Pass relative paths like 'bear/arch-overview.md' or 'external/jira-ticket.md'. Use after reading the index to load only relevant files — never load everything.

Risk signalsBulk/mass operation — affects multiple targets

Part of the Better Bear server.

bear_context_fetch is read-only, but an agent in a loop can still rack up calls and cost. PolicyLayer caps every call before it runs. Live in minutes.

SECURE BETTER BEAR →

Free to start. No card required.

AI agents call bear_context_fetch to retrieve information from Better Bear without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.

Even though bear_context_fetch only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.

Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "bear_context_fetch": {}
  }
}

See the full Better Bear policy for all 35 tools.

Get this rule live on your own Better Bear server in minutes. PolicyLayer enforces it on every call, before it runs.

ENFORCE ON MY BETTER BEAR →

View all 35 tools →

These attack patterns abuse exactly the kind of access bear_context_fetch gives an agent. Each links to the full case and the policy that stops it:

Browse the full MCP Attack Database →

Every attack above starts with a tool call. PolicyLayer checks each one against your policy first, so bear_context_fetch only ever does what you allow.

SECURE BETTER BEAR →

Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.

What does the bear_context_fetch tool do? +

Load the full content of specific files from the context library. Pass relative paths like 'bear/arch-overview.md' or 'external/jira-ticket.md'. Use after reading the index to load only relevant files — never load everything.. It is categorised as a Read tool in the Better Bear MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on bear_context_fetch? +

Register the Better Bear MCP server in PolicyLayer and add a rule for bear_context_fetch: 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 Better Bear. Nothing to install.

What risk level is bear_context_fetch? +

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

Can I rate-limit bear_context_fetch? +

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

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

bear_context_fetch is provided by the Better Bear MCP server (better-bear). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Better Bear tool call.

Deterministic rules across all 35 Better Bear tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.