Intaris MCP Server

Intaris needs an OpenAI-compatible API key for safety evaluation. It picks up `LLM_API_KEY` from your environment automatically.

Remote serverstreamable-httpPython

What is the Intaris MCP server?

Most AI and media services work still happens through a UI a human drives. Intaris MCP server moves it into the conversation instead. Intaris needs an OpenAI-compatible API key for safety evaluation. It picks up LLM_API_KEY from your environment automatically.

The short version

  • Default-deny classifier — -- Explicit read-only allowlist with critical pattern detection. Everything not allowlisted goes through LLM evaluation
  • LLM safety evaluation — -- OpenAI-compatible structured output for alignment checking, risk assessment, and decision reasoning
  • Priority-ordered decision matrix — -- Critical risk auto-denies, aligned low/medium approves, high risk and misalignment escalate for human review
  • Session management — -- Hierarchical parent/child sessions with intention tracking, lifecycle states, and idle sweep
  • Intention tracking — -- User-driven intention model with IntentionBarrier for real-time updates and AlignmentBarrier for parent/child enforcement
  • MCP proxy — -- Sits between clients and upstream MCP servers, evaluating every tool call with per-tool preference overrides

Getting it running

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

The tools it exposes

The server publishes 7 tools. What each one is for:

  • Default — deny classifier** -- Explicit read-only allowlist with critical pattern detection. Everything not allowlisted goes through LLM evaluation
  • Priority — ordered decision matrix** -- Critical risk auto-denies, aligned low/medium approves, high risk and misalignment escalate for human review
  • Cognis — ready auth** -- Accepts Cognis-issued ES256 JWTs for service-to-service calls while keeping standalone API key auth for direct clients
  • Client — Integration
  • Metric — Value
  • Precision — 100%
  • Document — Description

What it needs from you

Configuration is passed through the environment: INTARIS_URL, LLM_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Things to watch

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

How it compares

Plenty of AI and media services servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Intaris's toolset — Default, Priority, Cognis and 4 more — is a fair guide to whether it matches your workflow. It is maintained by fpytloun; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Available tools

ToolWhat it does
Defaultdeny classifier** -- Explicit read-only allowlist with critical pattern detection. Everything not allowlisted goes through LLM evaluation.
Priorityordered decision matrix** -- Critical risk auto-denies, aligned low/medium approves, high risk and misalignment escalate for human review.
Cognisready auth** -- Accepts Cognis-issued ES256 JWTs for service-to-service calls while keeping standalone API key auth for direct clients.
ClientIntegration
MetricValue
Precision100%
DocumentDescription

How to install the Intaris MCP server

{
  "mcpServers": {
    "intaris": {
      "command": "uvx",
      "args": ["intaris"],
      "env": {
        "INTARIS_URL": "your-value",
        "LLM_API_KEY": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
INTARIS_URLEndpoint or connection string the server talks to.Yes
LLM_API_KEYCredential the server authenticates with.Yes

Example prompts to try

  • Use Intaris to Default.
  • Use Intaris to Priority.
  • Use Intaris to Cognis.

Frequently asked questions

It connects Intaris to MCP-compatible AI assistants such as Claude and Cursor, exposing 7 tools (Default, Priority, Cognis, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Intaris directly.