mcpField
O
OntoRamp Graph Query

OntoRamp Graph Query

Remote
github.com/MatthewDavisAIArchitectMemory & Knowledge0Updated 10w ago
Repository

About OntoRamp Graph Query

OntoRamp Graph Query is a hosted MCP server for AI agents and LLM workflows that need organizational architecture and governance context. It returns answers tied to evidence chains rather than document similarity.

Key features

  1. 01Architecture queries grounded in documented structure
  2. 02Governance constraint signals
  3. 03System and component dependency tracing
  4. 04Evidence chains for architectural claims
  5. 05Agentic Readiness Assessment requests

Use cases

  1. 01Check governance constraints before a proposed action
  2. 02Trace dependencies affected by an architecture change
  3. 03Review evidence supporting or challenging a claim

MCP support

Exposes architecture, governance, dependency, evidence, and assessment tools to MCP clients over Streamable HTTP.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://ontoramp-graph-query.fly.dev/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

All endpoints
Streamable HTTPhttps://ontoramp-graph-query.fly.dev/mcpAuth required

Tools

Details

From the project README

OntoRamp

OntoRamp Graph Query — MCP Server

The MCP server that answers "what does governance say about this?" — evidence-grounded answers from a curated architecture and governance knowledge base, not a document dump.

Problem: AI agents act blindly against organizational architecture. They don't know what the org has already decided, what constraints apply, or what the existing structure says about a proposed action.

Solution: Query a curated architecture and governance knowledge base directly from any AI agent or LLM workflow. Returns evidence-grounded answers with citation chains — not document similarity. Works from day one, and grows as your organization seeds its own knowledge.

MCP Registry License Status


Tools

ToolDescriptionTier
query_architectureQuery organizational architecture for answers grounded in documented structureFree
get_constraint_signalsSurface governance constraints relevant to a proposed action or decisionFree
find_dependenciesTrace dependencies between systems and components in your architectureDeveloper+
get_evidence_for_claimReturn evidence chains supporting or contradicting an architectural claimDeveloper+
request_assessmentSubmit an Agentic Readiness Assessment requestAll tiers, rate-limit exempt

Tiers

TierPriceLimitsFeatures
Free— (no credit card)10 queries/dayquery_architecture + get_constraint_signals
Developer$0.015/callUnlimitedAll tools · Evidence provenance · Query history
Org$249/mo flatUnlimitedAggregate architecture health · Cross-agent pooling · ARA pre-population

request_assessment is exempt from rate limits on every tier.

Install

OntoRamp Graph Query is a hosted, remote MCP server (Streamable HTTP) — nothing to install, build, or run locally. See llms-install.md for an agent-followable walkthrough.

1. Get a free API key at ontoramp.com/mcp (no credit card). It arrives by email as or_free_….

2. Add to Cline — edit ~/.cline/mcp.json (or use the Cline UI → MCP Servers → Configure):

{
  "mcpServers": {
    "ontoramp-graph-query": {
      "url": "https://ontoramp-graph-query.fly.dev/mcp",
      "headers": { "Authorization": "Bearer YOUR_API_KEY" },
      "disabled": false,
      "autoApprove": []
    }
  }
}

Other MCP clients (Claude Desktop, etc.) use the same mcpServers shape (url + headers). Transport is Streamable HTTP.

3. Verify — curl https://ontoramp-graph-query.fly.dev/health → {"status":"ok","version":"1.0.0","server":"ontoramp-graph-query"}.

See examples/usage.md for example calls.

ARA Trigger

When get_evidence_for_claim surfaces evidence coverage gaps, the server prompts:

Your architecture coverage has gaps that a manual review won't surface. An Agentic Readiness Assessment will diagnose your current state and build a prioritized remediation plan. Schedule at ontoramp.com/assess.

Security

  • All responses are audited for public release — no scoring-formula internals, no substrate architecture details
  • Your data is scoped to your tenant namespace and never shared across organizations
  • Free-tier keys are read-scoped; Developer/Org keys require account authentication
  • GET /health returns live status

Support


Governed by OntoRamp Governance Physics. OntoRamp LLC · ontoramp.com

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.