Connects AI clients to a personal neural network and workspace to manage memory, coordinate agents, and execute tasks across work, people, and life.
Also known as Richard-Ewing/exogram-sdk, exogram-sdk, mcp-server-exogram
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- 101
- Latest version
- 0.2.3
- Last commit
- Oct 30, 2026
- License
- MIT
What is Exogram MCP?
Exogram connects AI clients to a personal neural network and workspace to manage memory, coordinate agents, and execute tasks across work, people, and life.
Summary generated from the project's README
About Exogram MCP server
Exogram provides a personal neural network and workspace designed to manage memory and coordinate tasks across work, people, and life. It functions as an intelligent bridge that connects AI clients like Claude Desktop, Cursor, and Google Antigravity to a centralized personal vault. Users can run the system locally using an embedded SQLite WAL engine in a zero-signup mode, or connect to the Exogram Cloud by providing an API key.
The system utilizes specialized cognitive kernels to handle tasks ranging from web scouting to analytical synthesis. It features a unique governance layer called the Instinct Pre-Mutation Action Gate, which uses state-hash drift guards to ensure all tool mutations are approved. Developers can interact with this ecosystem through official Python and TypeScript SDKs, allowing for complex memory retrieval using spreading activation and HippoRAG 2 algorithms. The server also supports A2UI Living Tiles, which are structured JSON schemas used to render interactive widgets like decision matrices and action drafts directly within the interface.
What you can do with it
- 1Retrieve complex personal contextAsk the AI to find specific technical decisions or personal details by traversing multi-hop associative paths across different life spheres.
- 2Securely execute governed actionsRequest the agent to perform a deployment or send a message while ensuring the action passes through a deterministic safety gate.
- 3Store and organize life dataRecord important information such as architecture decisions or personal traits into a local or cloud-based vault.
- 4Generate interactive workspace widgetsHave the AI present information using structured visual components like comparison tables or checklists.
Written from the project's README. Every use case is checked against a quote from it.
How to install Exogram MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Exogram MCP in Claude Code
$ claude mcp add --env 'EXOGRAM_BEARER_TOKEN=<YOUR_EXOGRAM_BEARER_TOKEN>' exogram-sdk -- uvx mcp-server-exogramInstall Exogram MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"exogram-sdk": {
"command": "uvx",
"args": [
"mcp-server-exogram"
],
"env": {
"EXOGRAM_BEARER_TOKEN": "<YOUR_EXOGRAM_BEARER_TOKEN>"
}
}
}
}Install Exogram MCP in VS Code
.vscode/mcp.json
{
"servers": {
"exogram-sdk": {
"type": "stdio",
"command": "uvx",
"args": [
"mcp-server-exogram"
],
"env": {
"EXOGRAM_BEARER_TOKEN": "<YOUR_EXOGRAM_BEARER_TOKEN>"
}
}
}
}Install Exogram MCP in VS Code CLI
$ code --add-mcp '{"name":"exogram-sdk","type":"stdio","command":"uvx","args":["mcp-server-exogram"],"env":{"EXOGRAM_BEARER_TOKEN":"<YOUR_EXOGRAM_BEARER_TOKEN>"}}'Install Exogram MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"exogram-sdk": {
"command": "uvx",
"args": [
"mcp-server-exogram"
],
"env": {
"EXOGRAM_BEARER_TOKEN": "<YOUR_EXOGRAM_BEARER_TOKEN>"
}
}
}
}Install Exogram MCP in Codex
$ codex mcp add exogram-sdk --env 'EXOGRAM_BEARER_TOKEN=<YOUR_EXOGRAM_BEARER_TOKEN>' -- uvx mcp-server-exogramInstall Exogram MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.exogram-sdk] command = "uvx" args = ["mcp-server-exogram"] [mcp_servers.exogram-sdk.env] EXOGRAM_BEARER_TOKEN = "<YOUR_EXOGRAM_BEARER_TOKEN>"
Install Exogram MCP in Gemini CLI
$ gemini mcp add -s user -e 'EXOGRAM_BEARER_TOKEN=<YOUR_EXOGRAM_BEARER_TOKEN>' exogram-sdk uvx -- mcp-server-exogramInstall Exogram MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"exogram-sdk": {
"command": "uvx",
"args": [
"mcp-server-exogram"
],
"env": {
"EXOGRAM_BEARER_TOKEN": "<YOUR_EXOGRAM_BEARER_TOKEN>"
}
}
}
}Configuration
EXOGRAM_BEARER_TOKENSecretExogram API Key from https://exogram.ai/dashboard/api (omit for zero-signup local SQLite mode)
EXOGRAM_API_KEYEXOGRAM_API_URLExogram API base URL (default: https://api.exogram.ai)
| Name | Description | |
|---|---|---|
| EXOGRAM_BEARER_TOKEN | Exogram API Key from https://exogram.ai/dashboard/api (omit for zero-signup local SQLite mode) | Secret |
| EXOGRAM_API_KEY | — | |
| EXOGRAM_API_URL | Exogram API base URL (default: https://api.exogram.ai) |
Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work · What to fix for more points
- Source repository linked and reachablerichard-ewing/exogram-sdk is public and reachablegithub.com/richard-ewing/exogram-sdk ↗Pass
- Package names this repository as its sourcemcp-server-exogram names https://github.com/Richard-Ewing/servers/issues as its sourcepypi.org/project/mcp-server-exogram/ ↗Finding
- Build provenance (Sigstore attestation)No build attestation published for this releaseNot checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-30github.com/richard-ewing/exogram-sdk ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from mcp-server-exogramPass
- No critical advisory in the package or its dependencies32 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeinitialize answered with protocol 2025-06-18 in 264 msPass
README
View on GitHubExogram Open-Core SDK & FastMCP Server (v0.2.0)
Exogram (exogram.ai) is a Personal AI Agent and workspace that understands your whole story across your work, people, and everyday life—coordinating specialist agents, turning plain requests into finished interactive deliverables, and executing real tasks with your approval.
This open-core repository provides the official Python/TypeScript SDKs and MCP bridge (mcp-server-exogram) so external AI tools (Claude, Cursor, Windsurf, VS Code, Google Antigravity) can connect directly into that same Exogram Personal Neural Network, interactive widget engine, and action-approval guardrails.
This open-core repository ships the runnable client libraries, local SQLite WAL engine, FastMCP server, and A2UI Living Tile JSON schemas:
python/(exogramv0.2.0) — Python SDK with Zero-Signup Local SQLite WAL Mode (~/.exogram/vault.db) and Cloud API routing (https://api.exogram.ai).typescript/(@exogram/sdkv0.2.0) — TypeScript & Node.js SDK with CJS/ESM/DTS builds and zero-signup local mode.mcp-server/(mcp-server-exogramv0.2.0) — FastMCP Server for Claude Desktop, Cursor, Google Antigravity, and OpenAI Agents.schemas/living-tiles-v5.schema.json— Canonical JSON Schema for all Composable A2UI Living Tiles and the 6 First-Party Kernels.
60-Second Zero-Signup Quickstart (Local SQLite WAL & Cloud)
Every SDK and MCP tool runs immediately on your machine using an embedded SQLite WAL vault (~/.exogram/vault.db) with zero account signup or API key required. When you set EXOGRAM_API_KEY, the exact same code routes to Exogram Cloud (https://exogram.ai).
1. Run the Python SDK in 30 Seconds
pip install exogram
# Or install directly from source:
pip install git+https://github.com/Richard-Ewing/exogram-sdk.git
from exogram import ExogramClient
# Automatically initializes ~/.exogram/vault.db (SQLite WAL) when no API key is set,
# or routes to https://api.exogram.ai when api_key="exo_live_..." or EXOGRAM_API_KEY is set.
client = ExogramClient()
# 1. Store memory claims across Work, People, and Life spheres
record = client.vault.store(
"Architecture decision: Production edge deploys to Cloudflare Workers via OpenNext",
namespace="work",
sphere="Work",
confidence=0.98,
temporal_horizon="durable_trait",
)
print(f"Stored {record.id} | State Hash: {record.state_hash}")
# 2. Traverse the Personal Neural Network (Infinite-Hop Spreading Activation + HippoRAG 2 PPR)
context = client.neural_network.retrieve(
query="How does our production edge deploy?",
spheres=["Work", "People", "Life"],
max_hops=4,
)
print(f"PPR Converged: {context.ppr_converged} | Claims: {len(context.claims)}")
# 3. Deterministic 0.07ms State-Hash & Instinct Pre-Mutation Action Gate
judgment = client.governance.evaluate_action(
agent_id="deployment-sentinel",
action_type="deploy_cloudflare_worker",
parameters={"service": "exogram-edge", "environment": "production"},
state_hash=context.state_hash,
)
if judgment.permitted:
receipt = client.actions.execute(judgment.execution_token)
print(f"Committed! Ledger Hash: {receipt.ledger_hash}")
Or run the self-contained demo script directly from this repository:
python examples/quickstart_local_and_cloud.py
2. Connect Claude Desktop, Cursor, or Antigravity via FastMCP (<30s)
Option A: Zero-Signup Local SQLite WAL Mode (~/.exogram/vault.db)
{
"mcpServers": {
"exogram": {
"command": "uvx",
"args": ["mcp-server-exogram", "--local"]
}
}
}
Option B: Hosted Exogram Cloud MCP (https://exogram.ai/api/mcp)
{
"mcpServers": {
"exogram": {
"command": "uvx",
"args": ["mcp-server-exogram"],
"env": {
"EXOGRAM_API_KEY": "exo_live_your_key_here",
"EXOGRAM_API_URL": "https://api.exogram.ai"
}
}
}
}
3. TypeScript / Node.js Quickstart (@exogram/sdk)
npm install @exogram/sdk
import { ExogramClient } from '@exogram/sdk';
const client = new ExogramClient(); // Zero-signup local mode or pass { apiKey: process.env.EXOGRAM_API_KEY }
const rec = await client.vault.store('Deploy target is Cloudflare Workers Global Edge', {
namespace: 'work',
sphere: 'Work',
confidence: 0.96,
});
const context = await client.neuralNetwork.retrieve('What is our deploy target?', {
spheres: ['Work', 'People', 'Life'],
maxHops: 4,
});
const judgment = await client.governance.evaluateAction({
agentId: 'ts-agent',
actionType: 'deploy_worker',
parameters: { target: 'cloudflare' },
stateHash: context.stateHash,
});
if (judgment.permitted && judgment.executionToken) {
const receipt = await client.actions.execute(judgment.executionToken);
console.log('Committed Ledger Hash:', receipt.ledgerHash);
}
Architecture Overview (Master Plan v5)
┌──────────────────────────────────────────────────────────────────────────────┐
│ User Prompt / External MCP Agent Call │
└──────────────────────────────────────┬───────────────────────────────────────┘
▼
┌──────────────────────────────────────────────────────────────────────────────┐
│ 1. Laya System 1 Deterministic Fast-Path (<15ms In-Memory Understanding) │
│ Resolves vault subjects, intent, sphere routing (Work · People · Life), │
│ and search queries in <15ms over profileDigest + priorTurns. │
└──────────────────────────────────────┬───────────────────────────────────────┘
▼
┌──────────────────────────────────────────────────────────────────────────────┐
│ 2. Personal Neural Network (Infinite-Hop Spreading Activation + HippoRAG 2) │
│ • Hybrid RRF Retrieval (Vector + BM25 + Entity Overlap) │
│ • Personalized PageRank (PPR, damping α = 0.85) across multi-hop edges │
│ • 3-Horizon Episodic Memory (ephemeral_episode, recurring_event, durable) │
│ • Read-Time/Write-Time Scalar Conflict Supersession & /api/memory/undo │
└──────────────────────────────────────┬───────────────────────────────────────┘
▼
┌──────────────────────────────────────────────────────────────────────────────┐
│ 3. Two-Tier Inference Gateway & 6 Honest First-Party Kernels │
│ • PERSONAL Subtasks → Paid Gemini 3.x (Zero PII leaves encrypted boundary)│
│ • PUBLIC_ONLY Subtasks → PII-stripped & compressed before Free-Token Pool │
│ • Post-Synthesis Citation Verification (Complete · Cited vs Standby) │
└──────────────────────────────────────┬───────────────────────────────────────┘
▼
┌──────────────────────────────────────────────────────────────────────────────┐
│ 4. Instinct Pre-Mutation Governance (0.07ms Gate) & A2UI Living Tiles │
│ • Deterministic SHA-256 State-Hash Drift Guard before any tool mutation │
│ • Progressive JSON Patching (AG-UI) & Claim-Predicate Entailment Scoring │
└──────────────────────────────────────────────────────────────────────────────┘
The 6 First-Party Cognitive Kernels
Every turn is orchestrated by six specialized first-party kernels and audited by verifyAgentContributionsAgainstTurnOutput so only kernels whose outputs are genuinely cited in the final synthesis display Complete · Cited:
| Kernel | Responsibility |
|---|---|
Neural Graph Kernel |
Traverses multi-hop associative paths across Work, People, and Life using Spreading Activation and HippoRAG 2 Spectral PPR. |
Generative UI Kernel |
Synthesizes and validates Composable A2UI Living Tiles against schemas/living-tiles-v5.schema.json. |
Live Web & Places Scout |
Executes PII-stripped public web & place verification for PUBLIC_ONLY subtasks. |
Action & Draft Kernel |
Prepares governed emails, calendar events, and external tool mutations gated by the 0.07ms Instinct Action Gate. |
Analytical Synthesis Kernel |
Performs multi-constraint reasoning, tradeoff matrices, and structured comparisons. |
Grounded Citation Kernel |
Enforces contrastive claim-predicate entailment (scoreClaimPredicateEntailment) and Perplexity-style [1], [2] citations. |
Composable A2UI Living Tiles (schemas/living-tiles-v5.schema.json)
Exogram dispatches structured inline Living Tiles validated for epistemic provenance:
action_draft— Governed outbound drafts (email, message, calendar, PR) with approval controls.checklist— Interactive execution checklists anchored to vault goals.decision_matrix— Multi-criteria weighted scoring tables.curated_places— Grounded venue & location cards with verified ratings.comparison_table— Side-by-side technical or product breakdowns.retail_deals_tile— Verified merchant pricing and availability cards.media_watch_tile— Film, series, book, and podcast recommendations with streaming provenance.occasion_countdown_tile— Recurring event (RRULE:FREQ=YEARLY) countdowns and preparation steps.memory_undo_tile— Transparent memory consolidation card with one-click/api/memory/undo.agent_hud_tile— Real-time telemetry of the 6 First-Party Kernels (Complete · CitedvsStandby).branded_diagram_tile— Publication-grade Plum Mineral (#FAF7F2,#201B20,#4C2B4B,#AEBD9A) SVG diagrams.hyperframes_video_tile— Frame-accurate deterministic HTML/CSS/SVG motion briefings (window.__renderFrame).instinct_computer_tile— Stateful browser/errand operator HUD withApprove StepandTake Overcontrols.
Repository Structure & Verification
exogram-sdk/
├── python/ # Official Python SDK (pip install exogram)
├── typescript/ # Official TypeScript SDK (npm install @exogram/sdk)
├── mcp-server/ # FastMCP Server (uvx mcp-server-exogram)
├── schemas/ # JSON Schemas (living-tiles-v5.schema.json)
├── examples/ # Runnable Local & Cloud Quickstart scripts
└── docs/assets/ # Plum Mineral UI previews & architecture diagrams
Run the Test Suites Locally
# 1. Run the 60-second quickstart script
python examples/quickstart_local_and_cloud.py
# 2. Run Python SDK unit tests
pytest python/tests/
# 3. Run FastMCP Server unit tests
pytest mcp-server/tests/
# 4. Run TypeScript SDK unit tests
cd typescript && npm test
License
MIT — see LICENSE for details.
Exogram MCP questions
How do I add Exogram MCP to Claude Code?
Run claude mcp add --env 'EXOGRAM_BEARER_TOKEN=<YOUR_EXOGRAM_BEARER_TOKEN>' exogram-sdk -- uvx mcp-server-exogram in your terminal. Add --scope user to make it available in every project.
How do I add Exogram MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
Do I need an account or API key to use Exogram locally?
No, you can run the SDK and MCP tools immediately using an embedded SQLite WAL vault with zero account signup or API key required.