Medium Risk

bridge_save_context

Remember something for later. Use this when the user says things like

How to control bridge_save_context ↓

What bridge_save_context does on Acheron

AI agents use bridge_save_context to create or update resources in Acheron — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Acheron environment.

Medium Risk

Why bridge_save_context needs a policy

This tool creates or modifies records in a local SQLite database to store context across sessions. It is a Write operation—reversible data modification (updates/inserts). Severity is medium because while the data persisted is user-controlled and not inherently destructive, misuse could involve storing sensitive information, injecting malicious prompts, or polluting the context store.

From the tool's definition Tool name 'bridge_save_context' and description 'Remember something for later' indicate persistent data creation/modification in SQLite backend.

Documented attack patterns abuse exactly the kind of access bridge_save_context gives an agent:

How to control bridge_save_context

PolicyLayer is an MCP gateway — it sits between your AI agents and Acheron, and nothing reaches the server without passing your rules. This is the rule we recommend for bridge_save_context:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "bridge_save_context": {
      "limits": [
        {
          "counter": "bridge_save_context_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

bridge_save_context stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Acheron — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about bridge_save_context

What does the bridge_save_context tool do? +

Remember something for later. Use this when the user says things like. It is categorised as a Write tool in the Acheron MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on bridge_save_context? +

Register the Acheron MCP server in PolicyLayer and add a rule for bridge_save_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 Acheron. Nothing to install.

What risk level is bridge_save_context? +

bridge_save_context is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit bridge_save_context? +

Yes. Add a rate_limit block to the bridge_save_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.

How do I block bridge_save_context completely? +

Set action: deny in the PolicyLayer policy for bridge_save_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.

What MCP server provides bridge_save_context? +

bridge_save_context is provided by the Acheron MCP server (timmx7/acheron-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Acheron tool call.

Start from Acheron, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

6 Acheron tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.