neuron_webagent_run

SERVERNeuron SOURCEneuron-mcp-server

High RISK CLASS

Category Execute

Parameters 122 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-conquext-neuron/neuron-webagent-run.md

WHAT IT DOES

What neuron_webagent_run does on Neuron

AI agents invoke neuron_webagent_run to trigger actions in Neuron. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.

Parameter	Type	Required	Description
`hop`	object	—	active posture: multi-hop navigation from seeds.
`url`	string	—	Optional page to open the mission on (else the platform home / active tab).
`caps`	object	—	Stop conditions.
`sink`	string	—	Where output goes (defaults to match the mission).
`seeds`	array	—	active posture: starting URLs (hashtag/search/profile pages) to crawl from.
`pacing`	string	—	Speed/rate (default normal).
`mission`	string	Yes	content = capture posts into a Collection; leads = capture prospects into the lead pool.
`posture`	string	—	How much it interacts (default read-light; 'active' enables hop + cinematic).
`leadTags`	array	—	leads mission: tags to attach to captured leads.
`platform`	string	Yes	ig=Instagram, x=X/Twitter, tk=TikTok, li=LinkedIn, fb=Facebook.
`cinematic`	object	—	active posture: cinematic reel/video capture.
`collectionName`	string	—	content mission: the Collection to fill (created if new).

Parameters from the server's own tool schema.

RISK

Why neuron_webagent_run is rated High

neuron_webagent_run triggers real processes with real consequences. An agent gone sideways doesn't fire it once. It starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.

Risk signalsAccepts URL/endpoint input (url) · High parameter count (21 properties)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs neuron_webagent_run safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Neuron, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For neuron_webagent_run, this is the rule to start with:

neuron_webagent_run Rate-limited

neuron_webagent_run stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "neuron_webagent_run": {
      "limits": [
        {
          "counter": "neuron_webagent_run_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Neuron, apply this rule, and every neuron_webagent_run call is checked against it from then on.

FAQ

Questions about neuron_webagent_run

What does the neuron_webagent_run tool do? +

Queue a browser mission for the user's Neuron extension to run — mine content into a Collection or prospects into the lead pool. Returns a command id; the extension picks it up on its next poll (so the browser must be open, signed in, and remote-control enabled in the extension). Watch it with neuron_webagent_list_runs / neuron_webagent_get_run and stop it with neuron_webagent_kill. It is categorised as a Execute tool in the Neuron MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

What parameters does neuron_webagent_run accept? +

neuron_webagent_run accepts 12 parameters: hop, url, caps, sink, seeds, pacing, mission, posture, leadTags, platform, cinematic, collectionName. Required: mission, platform. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on neuron_webagent_run? +

Register the Neuron MCP server in PolicyLayer and add a rule for neuron_webagent_run: 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 Neuron. Nothing to install.

What risk level is neuron_webagent_run? +

neuron_webagent_run is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit neuron_webagent_run? +

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

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

neuron_webagent_run is provided by the Neuron MCP server (neuron-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Neuron, and thousands of servers like it.

This server

All 401 Neuron tools → High-risk tools on this server →

Across the catalogue

editor_run_template on 010 Editor →run on 0sec →shortcuts_run on Apple Apps MCP →run_emba_scan on EMBA-MCP → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →