The server itself exposes 5 tools, and some of them can write to your Guru 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 Guru.

How is this different from connecting Guru 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 Guru MCP API changes?

We track the Guru 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 Guru 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 Guru?

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 Guru MCP server myself?

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

Connect Guru MCP to your AI agents, securely.

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

Get started for free

Get a demo

Try Guru MCP now

What your agents can ask once Guru MCP is connected.

Select the tools your AI agents can call

5 tools from the Guru MCP schema.

Showing 5 tools

List Knowledge AgentsreadDiscovers the Knowledge Agents available in the workspace.
AskreadAsks Guru a question and returns a verified answer, carrying the organization's own verification status with the content.
SearchreadFinds Guru cards or connected documents matching a keyword, returning permission-aware results.
Create DraftwriteCreates a draft card directly from an AI conversation. It produces a draft rather than a published card.
Update CardwriteSuggests updates to an existing card rather than committing them, so a person still decides whether the change lands.

What Guru MCP exposes

Guru MCP groups its 5 tools into 2 categories, each with a suggested starting policy.

All 5 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Knowledge Retrieval	Discovering the Knowledge Agents available in the workspace, asking Guru a question and getting back a verified answer, and searching for Guru cards or connected documents matching a keyword	Read	Read-only and filtered to what the authenticated person can already see, so this is the half of the server that is safe to allow freely. Ask returns verified answers, which means the output carries the organization's own review status with it
Authoring	Creating a draft card directly from an AI conversation, and suggesting updates to an existing card	Write	Neither publishes. A draft stays a draft and an update is a suggestion, so a person still decides what becomes company knowledge. Log them anyway, since a draft in a knowledge base is content colleagues will read

Connect Guru 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 Guru
Find Guru 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 Guru MCP or block it. You allow the exact tools each agent can call, one by one.

Guru 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 Guru 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.	Guru MCP5 capabilities documented by Guru. These are named as capabilities rather than exact tool identifiers, so the names here follow Guru's documentation. Results are permission-aware, the two write capabilities produce drafts and suggestions rather than published content, and Guru notes it may add new tools as the MCP standard evolves.
Coding assistants	Connection & credentialsper user	Knowledge Retrieval3 tools
Internal copilots	Tool access policiesdeny by default	Authoring2 tools
Workflow automations	Request & response inspectioninline
Compatible MCP clients	Activity monitoringalerts and logs