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

We track the Fibery 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 Fibery 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 Fibery?

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 Fibery MCP server myself?

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

Connect Fibery MCP to your AI agents, securely.

Q: Is Fibery MCP secure?

The server itself exposes 6 tools, and some of them can write to your Fibery 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 Fibery.

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

Get started for free

Get a demo

Try Fibery MCP now

What your agents can ask once Fibery MCP is connected.

Select the tools your AI agents can call

6 tools from the Fibery MCP schema.

Showing 6 tools

list_databasesreadRetrieves a list of all databases available in the Fibery workspace.
describe_databasereadProvides a detailed breakdown of a specific database's structure, showing all fields with their titles, names and types.
query_databasereadOffers flexible access to Fibery data through the Fibery API, so the shape of the result depends on the query the caller constructs.
create_entitywriteCreates a new entity in the Fibery workspace with specified field values.
create_entities_batchwriteCreates multiple new entities in the Fibery workspace with specified field values, in a single call.
update_entitywriteUpdates existing entities in the Fibery workspace with new field values.

What Fibery MCP exposes

Fibery MCP groups its 6 tools into 2 categories, each with a suggested starting policy.

All 6 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Schema & Query	Listing every database available in the workspace, breaking down a specific database's structure with all its fields, names and types, and querying Fibery data through the API	Read	describe_database is the prerequisite for a correct write, since field names and types come from there. query_database is flexible rather than fixed, so log the query and not just the call
Entities	Creating a new entity with specified field values, creating multiple entities in one call, and updating existing entities with new field values	Write	No delete tool exists, so the worst case is unwanted records rather than lost ones. create_entities_batch multiplies a single approval across many records, so cap the batch size at the gateway

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

Fibery MCP	6 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 6 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 Fibery 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.	Fibery MCP6 documented tools in fibery-mcp-server v0.1.8, a local Python stdio server installed through uv or Smithery, under the MIT licence. There is no OAuth: the Fibery host and an API token are passed as command-line arguments. No delete tool is exposed.
Coding assistants	Connection & credentialsper user	Schema & Query3 tools
Internal copilots	Tool access policiesdeny by default	Entities3 tools
Workflow automations	Request & response inspectioninline
Compatible MCP clients	Activity monitoringalerts and logs