AIAP
PLATFORMMETHODMCPPRICINGABOUTSign in
MCP-native

Agents read and build your architecture

Generate a scoped token and connect any MCP client — Claude Code, Claude Desktop — to your project endpoint. Reads return the full graph; writes go through validated tools.

Connect in minutes

Your architecture graph, the scoped MCP endpoint, and a Claude agent — reads and writes flowing both ways. Three steps from token to a building agent.

readwritereadwriteYour projectarchitecture graphaiap · mcpscoped tokenClaude agentreads + buildsone token · any MCP client · live in minutes
01

Generate a scoped token

Create a read or read+write bearer token for your project — sha256-hashed at rest and revocable anytime.

02

Paste it into your client

Point Claude Code, Claude Desktop, or any MCP client at your project endpoint with the token.

03

The agent reads & builds

Reads return the full graph; writes go through validated, audited tools — no separate brief required.

Safe by construction

The MCP endpoint runs server-side and re-derives the token user's org role on every call — it never bypasses your access model.

Scoped tokens

Per-user bearer tokens (read or read+write), sha256-hashed at rest, revocable at any time.

Validated tools

add / connect / arrange / remove components and connections are schema-checked and scoped to your membership and role.

Recorded

Every agent mutation is written to the activity log with source=mcp — fully auditable, same as a human edit.

claude · aiap mcpconnected
list_projectsread
get_architectureread
add_componentwrite
connect_componentswrite
update_componentwrite
→ validated · scoped · audited

The tools

A focused toolset that mirrors the app's own service layer — nothing an agent can do that a member couldn't do in the UI.

Read

list_orgs · list_projects · get_project · get_architecture · search_library — full context, no scraping.

Projects (architect+)

create_project · update_project · delete_project (owner) — scaffold and manage projects without leaving your agent.

Components (architect+)

add_container · add_component · update_component · remove_component — build the graph node by typed node.

Connections (architect+)

connect_components · remove_connection · arrange_architecture — wire and lay out the system.

Skills (owner)

list_skills · create_skill · update_skill · delete_skill — manage the org's reusable Copilot skills.

Grounded

The same graph the Copilot reads is the graph agents extend — one source of truth, no separate brief.

AIAP
architecture.inference.institute
PlatformMethodMcpPricingAboutSign in
© 2026 Inference Institute