How is this different from connecting Socket MCP directly?

Connected directly, an agent sees every tool the server exposes and holds the credential itself. Through TrustGate you choose which tools each agent gets, and every call is logged against the agent that made it.

What if the Socket MCP API changes?

We track the Socket MCP schema, so the tool catalogue stays current. Tools you have already allowed keep working, and anything new stays denied until you enable it.

Can I give different agents different Socket tools?

Yes. Access is set per agent: one can get a handful of read tools, another the full set. You grant the whole MCP or single tools within it.

Where can I see what my agents did in Socket?

Every call is logged against the agent that made it, with the tool it used. Activity can be sent on to your own monitoring.

Do I need to run the Socket MCP server myself?

No. TrustGate connects to the Socket MCP server and sits in front of it. Your agent only talks to your TrustGate URL, never to Socket directly.

Connect Socket MCP to your AI agents, securely.

Q: Is Socket MCP secure?

The server itself exposes 5 tools, and some of them can write to your Socket account. Behind TrustGate an agent only sees the tools you allow, requests and responses are inspected, and every call is logged. Anything outside the allowlist is denied before it reaches Socket.

One secured endpoint for every Socket call your AI agents make, scoped per user, inspected, and logged.

Get started for free

Get a demo

Try Socket MCP now

What your agents can ask once Socket MCP is connected.

Select the tools your AI agents can call

5 tools from the Socket MCP schema.

Showing 5 tools

depscorereadQueries the Socket API for dependency scoring. Takes an array of packages, each with a name and optional ecosystem (npm by default) and version, and returns supply chain, quality, maintenance, vulnerability and license scores for each one in a single request.
threat_feedreadLook up items in the Socket organization threat feed with the `threat_feed` tool.
package_file_contentsreadRead a single file from a package using the `package_file_contents` tool from Socket.
package_file_grepreadSearch a single file from a package for lines matching a JavaScript regular expression.
package_filesreadList the files published in a package using the `package_files` tool from Socket.

What Socket MCP exposes

Socket MCP groups its 5 tools into 1 categories, each with a suggested starting policy.

All 5 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Dependency Scoring	Security and quality scoring for packages across npm, PyPI, Cargo and other ecosystems, in batches, returning supply chain, quality, maintenance, vulnerability and license scores per package	Read	Read-only and safe to allow freely. The real control is a client rule that makes the agent score dependencies before adding them, since nothing forces the call

Connect Socket MCP to your AI agent

Four steps, under ten minutes.

01
Sign in to NeuralTrust
Open the NeuralTrust platform, sign in and go to Getting started, then Connect your tools.
02
Choose your agent
When asked which agent you use, pick Claude Code, Codex, Cursor, Windsurf, Copilot or your own code.
03
Connect Socket
Find Socket in the tool list and connect it.
04
Connect your agent
Follow the steps on screen to add the config to your agent, then send the test prompt.

Permissions down to the single tool

You do not allow Socket MCP or block it. You allow the exact tools each agent can call, one by one.

Socket MCP	5 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 5 tools

Tool by toolConnecting the server is not the unit of access. Each tool is granted on its own.
Default denyA tool you have not enabled is never exposed to the agent.
Approval on writesTools that change or delete things can require a human to confirm.

Is Socket MCP secure?

One endpoint instead of raw credentials. Every call is checked against policy and logged.

AI agentsConnect through your MCP client configuration.	NeuralTrustApply controls based on your configuration.	Socket MCP5 documented tools, read-only. The public server at mcp.socket.dev authenticates through the MCP client's OAuth flow, with no API key to copy or manage; local stdio and HTTP deployments are also available.
Coding assistants	Connection & credentialsper user	Dependency Scoring5 tools
Internal copilots	Tool access policiesdeny by default
Workflow automations	Request & response inspectioninline
Compatible MCP clients	Activity monitoringalerts and logs