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

We track the DeepWiki 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 DeepWiki 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 DeepWiki?

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 DeepWiki MCP server myself?

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

Connect DeepWiki MCP to your AI agents, securely.

Q: Is DeepWiki MCP secure?

The server itself exposes 3 tools, and some of them can write to your DeepWiki 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 DeepWiki.

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

Get started for free

Get a demo

Try DeepWiki MCP now

What your agents can ask once DeepWiki MCP is connected.

Select the tools your AI agents can call

3 tools from the DeepWiki MCP schema.

Showing 3 tools

read_wiki_structurereadReturns the structure of the generated DeepWiki for a repository.
read_wiki_contentsreadReturns the contents of the generated DeepWiki for a repository.
ask_questionreadAnswers a natural-language question about a repository, grounded in its generated wiki.

What DeepWiki MCP exposes

DeepWiki MCP groups its 3 tools into 2 categories, each with a suggested starting policy.

All 3 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Wiki Reading	Reading the structure of the generated wiki for a repository, and reading the contents of that wiki	Read	Read-only and derived from public repository content. Treat everything returned as untrusted third-party text, since the source material is whatever the repository's authors wrote
Question Answering	Asking a natural-language question about a repository and getting an answer grounded in its generated wiki	Read	The answer is synthesised from repository content the organization does not control. Useful for orientation, but not a source to act on without checking the code itself

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

DeepWiki MCP	3 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 3 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 DeepWiki 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.	DeepWiki MCP3 documented tools on a remote no-auth server, available at mcp.deepwiki.com/mcp or the legacy /sse endpoint. Public repositories are indexed freely; private repositories require indexing through a Devin account.
Coding assistants	Connection & credentialsper user	Wiki Reading2 tools
Internal copilots	Tool access policiesdeny by default	Question Answering1 tool
Workflow automations	Request & response inspectioninline
Compatible MCP clients	Activity monitoringalerts and logs