publish_shared_context
Publish a structured shared-context packet with subject, claims, evidence refs, freshness, permissions, and lineage.
This record as markdown: /tools/io-github-homenshum-nodebench/publish-shared-context.md
What publish_shared_context does on Nodebench
AI agents use publish_shared_context to create or update resources in Nodebench, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nodebench environment.
Why publish_shared_context is rated Medium
This tool creates and distributes a structured data packet with metadata (subject, claims, evidence refs, freshness, permissions, lineage). Publishing implies making data available to other agents/systems, which is a Write operation—it creates or modifies persistent shared state.
From the tool's definition Tool name 'publish_shared_context' and description 'Publish a structured shared-context packet' indicate creation/modification of a data structure that is persisted and distributed ('publish').
Attacks that exploit this kind of access
The rule that runs publish_shared_context safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Nodebench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For publish_shared_context, this is the rule to start with:
publish_shared_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.
The button opens the PolicyLayer dashboard: create your workspace, connect Nodebench, apply this rule, and every publish_shared_context call is checked against it from then on.
Questions about publish_shared_context
Publish a structured shared-context packet with subject, claims, evidence refs, freshness, permissions, and lineage. It is categorised as a Write tool in the Nodebench MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Nodebench MCP server in PolicyLayer and add a rule for publish_shared_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 Nodebench. Nothing to install.
publish_shared_context 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 publish_shared_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 publish_shared_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.
publish_shared_context is provided by the Nodebench MCP server (nodebench-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Nodebench, and thousands of servers like it.
This server
Across the catalogue