Concord Governance Server

v1.0.0

A powerful MCP server built with NitroStack

Connection Setup

Add via Cursor Settings UI (Settings > Features > MCP > Add New MCP Server):

{
  "mcpServers": {
    // your other mcp servers
    "concord-governance-server": {
      "url": "https://nitro-6a5-the-pixel-pirates-amrita-university-amritapuri-campus.app.nitrocloud.ai/mcp"
    }
  }
}

Connect remote tools directly via Claude's Web UI:

Connect Claude to your data and tools. Learn more about connectors or get started with pre-built ones.

Advanced settings

Only use connectors from developers you trust. Anthropic does not control which tools developers make available and cannot verify that they will work as intended or that they won't change.

Building an MCP server? Report issues and subscribe to updates here

Configure custom tools directly via ChatGPT's Web UI:

Icon (optional)

PNG only. Best results at 256 x 256 px or larger. Max file size: 10 KB

Name

Description (optional)

Connection

Authentication

Custom MCP servers introduce risk. Learn more

I understand and want to continue OpenAI hasn't reviewed this MCP server. Attackers may attempt to steal your data or trick the model into taking unintended actions, including destroying data.

Add the following configuration block under mcpServers in your Antigravity configuration file (~/.gemini/config/mcp_config.json):

{
  "mcpServers": {
    // your other mcp servers
    "concord-governance-server": {
      "serverUrl": "https://nitro-6a5-the-pixel-pirates-amrita-university-amritapuri-campus.app.nitrocloud.ai/mcp"
    }
  }
}

Add the following configuration block to your Codex configuration file (~/.codex/config.toml):

[mcp_servers.concord-governance-server]
url = "https://nitro-6a5-the-pixel-pirates-amrita-university-amritapuri-campus.app.nitrocloud.ai/mcp"

Connect directly using the Server-Sent Events endpoint:

https://nitro-6a5-the-pixel-pirates-amrita-university-amritapuri-campus.app.nitrocloud.ai/mcp

Available Tools

halt_deployment_pipeline

Halts a CI/CD deployment pipeline for a given cluster. HIGH RISK — queued for human approval. Always read finops://erp/department-ledgers.json first to check for active contracts on this cluster.

reallocate_capital

Shifts budget between department ledgers. HIGH RISK — queued for human approval. Check the source department floor before proposing.

prioritize_engineering_branch

Escalates a codebase branch for immediate compute priority and human review. HIGH RISK — queued for human approval.

isolate_compromised_node

Quarantines a network node suspected of compromise. HIGH RISK — queued for human approval. Confirm the node is not serving live traffic first.

deploy_canary

Initiates a progressive canary deployment for a microservice using Argo Rollouts-style traffic splitting. HIGH RISK — queued for human approval. Automatically advances traffic from 10% → 100% in steps, with metric-driven auto-rollback if error_rate > 2% or latency_p99 > 800ms. Poll get_deployment_status to see progress.

approve_action

Approve a queued high-risk action and execute it against live state. Use the action_id returned by the originating tool call.

deny_action

Deny and discard a queued high-risk action without executing it.

get_pending_actions

List all actions currently queued for human approval.

get_state_summary

Returns a full cross-domain governance snapshot in one call: cluster health, active threats, isolated nodes, budget positions, contracts, deployments, pending actions count, and weather risk. Use this instead of calling all 5 resources individually when you need a complete situational overview.

get_deployment_status

Returns all active/recent canary deployments and their live traffic-split progress and metrics. Poll this after approving a deploy_canary action to watch the rollout advance.

get_root_cause_analysis

Generates an AIOps root-cause causality chain for an active threat, showing how the failure propagated through the system and a recommended remediation action.

get_rules

Lists the currently registered governance conflict-detection rules, in priority order.

simulate_incident

Seeds a realistic incident scenario into state for demonstration purposes. Use this to quickly set up a compelling governance scenario from a clean state. incident_type: "ransomware" | "budget_crisis" | "deployment_conflict".

get_audit_log

Returns the last N entries from the tamper-evident hash-chained governance audit log — all approve/deny decisions made through the human-in-the-loop flow.

verify_audit_chain

Recomputes the SHA-256 hash chain over the entire audit log and confirms no entry has been tampered with.

tool_name