GIA - Governed Intelligence Architecture MCP Server

Governance enforcement layer for generative AI agents. Classify every decision, enforce human approval gates, control what agents can access, score compliance posture, and maintain a cryptographic audit trail. Works with any MCP-compatible AI client or agent framework - model-agnostic and vendor-neutral. Its 40 documented tools cover board, memory, pack, verify.

People connecting this server to Claude, Cursor, VS Code, or another MCP client. The project is written in TypeScript.

VERIFIED ACTIVE

LAST COMMIT 2026-07-30 · ★ 3 · #279 OF 848 MAINTAINED OTHER · VERIFIED 2026-08-25

NOASSERTION · TypeScript servers · how we verify → /methodology

01 · Install GIA - Governed Intelligence Architecture

Claude Code

claude mcp add knowledgepa3-gia-mcp-server --transport http https://gia.aceadvising.com/mcp

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "knowledgepa3-gia-mcp-server": {
      "url": "https://gia.aceadvising.com/mcp"
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

https://gia.aceadvising.com/mcp

transport: streamable-http

endpoint alive - authentication required · probed 2026-08-25

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions · remote - your agent's requests go to gia.aceadvising.com

endpoint auth requires authentication - rejected our unauthenticated MCP initialize

license no standard license detected - usage rights unclear; check the repo before commercial use

npm package gia-mcp-server - unscoped; check the name against the project README before installing

registry namespace io.github.knowledgepa3 is GitHub-verified and matches the repo owner

03 · What GIA - Governed Intelligence Architecture can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

What you can build

With this server connected, an agent can map controls to NIST AI RMF, EU AI Act, ISO 42001, NIST 800-53, FedRAMP, LINDDUN, MITRE ATLAS, OMB, report which tools are available at your current tier, and which are withheld, request a governed LLM completion via MCP Sampling - the client makes the model call, GIA governs whether and under what constraints, and create hash-sealed, TTL-bound institutional knowledge artifacts.

Capability map

Tools grouped from the project's README - what GIA - Governed Intelligence Architecture lets an agent do.

Board

7 tools - e.g. List governed institutions (e.g. Architecture Review Board, Federal AI Council); List charters under an institution with modes and seat configuration; Convene a deliberation session - each seat…

board_list_institutions · board_list_charters · board_convene_session · board_get_session · board_install_kit · board_approve_gate…

Verify

3 tools - e.g. Self-consistency check of the in-memory hash chain from genesis (see the honesty note below); Verify ledger chain, agent health, threshold, and intelligence-layer continuity; Verify the persisted…

verify_ledger · phoenix_verify_integrity · verify_ledger_v2

Evaluate

2 tools - e.g. Storey Threshold escalation-rate health metric; Model-routing health: fallback rate, cache hit rate, batch utilization, premium spend leakage

evaluate_threshold · evaluate_routing_threshold

read & search

2 tools - e.g. Report which tools are available at your current tier, and which are withheld; Wait on a MANDATORY gate after classify_decision returns PENDING; polls up to 60s

list_available_tools · get_gate_status

Phoenix

2 tools - e.g. Create a governed state snapshot, hash-chained to the previous one; Assess disaster-recovery readiness (NIST CP-2 / CP-9 / CP-10)

phoenix_snapshot · phoenix_recovery_health

Generate

2 tools - e.g. Governance status report (summary, detailed, or executive); Economic + governance impact report (an illustrative estimate, labelled as such)

generate_report · generate_impact_report

Record

2 tools - e.g. Record time saved, risk blocked, success rate, autonomy level; Record gates triggered, drift prevented, violations blocked, human interventions

record_value_metric · record_governance_event

Agent

2 tools - e.g. Query and exercise constitutional agent rights; get structured rejection explanations; Query agent citizenship tier and merit score, or trigger re-evaluation

agent_rights · agent_citizenship_status

Latest releases

v0.2.1 · 2026-02-26

Changes · Added mcpName field to package.json for official MCP Registry compatibility · Published to registry.modelcontextprotocol.io as io.github.knowledgepa3/gia-mcp-server · Added server.json registry metadata…

v0.2.0 · 2026-02-26

What's New · Architecture change: GIA MCP Server is now a lightweight proxy to the hosted governance engine at gia.aceadvising.com. All governance logic runs server-side - zero IP ships in the npm package. · Setup…

04 · Who maintains GIA - Governed Intelligence Architecture

GIA - Governed Intelligence Architecture is maintained by knowledgepa3. It's the only MCP server we track from this author; the repo dates to Feb 2026.

05 · Facts

category
other - ranked #279 of 848 actively-maintained other servers as of 2026-08-25.
registry
io.github.knowledgepa3/gia-mcp-server (active, first published 2026-02-26 · 4 versions)
packages
npm:gia-mcp-server

06 · GIA - Governed Intelligence Architecture FAQ

Is GIA - Governed Intelligence Architecture still maintained?

Yes - as of 2026-08-25, its last commit was 2026-07-30. We re-verify nightly.

What can GIA - Governed Intelligence Architecture do?

With this server connected, an agent can map controls to NIST AI RMF, EU AI Act, ISO 42001, NIST 800-53, FedRAMP, LINDDUN, MITRE ATLAS, OMB, report which tools are available at your current tier, and which are withheld, request a governed LLM completion via MCP Sampling - the client makes the model call, GIA governs whether and under what constraints, and create hash-sealed, TTL-bound institutional knowledge artifacts.

How do I install GIA - Governed Intelligence Architecture?

Run `npx -y gia-mcp-server`. You can also paste the ready-made client config above.

Does GIA - Governed Intelligence Architecture require authentication?

Yes - when we probed the endpoint on 2026-08-25, it rejected an unauthenticated MCP initialize; you'll need credentials to connect.

07 · Alternatives to GIA - Governed Intelligence Architecture

More MCP servers to compare · MoldSim MCP Server · Porkbun MCP · Hermes Atlas MCP · Aftereffects · Better Bear

More TypeScript MCP servers · World Monitor · Kolonie AI · Komnet · Kontent Ai MCP Server · see all