# Exogram — Personal AI Agent & Workspace (remote · api.exogram.ai)

Official MCP bridge to Exogram—the Personal AI Agent for your work, people, and life.

- Trust score: 71/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `api.exogram.ai`: 71/100 (this document), [markdown](https://verifymcp.io/servers/richard-ewing-exogram/api.md), [page](https://verifymcp.io/servers/richard-ewing-exogram/api)
- pypi · `mcp-server-exogram`: 39/100, [markdown](https://verifymcp.io/servers/richard-ewing-exogram/mcp-server-exogram.md), [page](https://verifymcp.io/servers/richard-ewing-exogram/mcp-server-exogram)

## Channel facts

- Endpoint: `https://api.exogram.ai/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.2.3`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 22 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 81/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1582 tokens (~65/item across 24 items; 22 tools + 2 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 22 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 24 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Exogram — Personal AI Agent & Workspace MCP server?

Exogram — Personal AI Agent & Workspace is a hosted endpoint at https://api.exogram.ai/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http richard-ewing-exogram 'https://api.exogram.ai/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "richard-ewing-exogram": {
      "url": "https://api.exogram.ai/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "richard-ewing-exogram": {
      "type": "http",
      "url": "https://api.exogram.ai/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.richard-ewing-exogram]
url = "https://api.exogram.ai/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "richard-ewing-exogram": {
      "type": "remote",
      "url": "https://api.exogram.ai/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add richard-ewing-exogram --url 'https://api.exogram.ai/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  richard-ewing-exogram:
    url: "https://api.exogram.ai/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "richard-ewing-exogram": {
      "Transport": "http",
      "Url": "https://api.exogram.ai/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add richard-ewing-exogram -t streamable-http -u 'https://api.exogram.ai/mcp'
```

### Other

```json
{
  "mcpServers": {
    "richard-ewing-exogram": {
      "type": "http",
      "url": "https://api.exogram.ai/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-30 (score 68, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-29 (score 68)

First indexed and scored.

## MCP tools (22)

### `search_vault` (~69 tokens)

Semantic and keyword search across stored personal records, facts, and memories in the private vault.

Input parameters:

- `query` (string, required): The search query to match against stored memories, project decisions, or preferences.
- `top_k` (number): Number of results to return (1-20, default 5).

### `search_memory_vault` (~73 tokens)

Search the Exogram Personal Neural Network and encrypted memory vault across facts, people, preferences, and commitments.

Input parameters:

- `query` (string, required): The search query to match against stored memories, relationships, or project context.
- `top_k` (number): Number of results to return (1-20, default 5).

### `store_memory` (~61 tokens)

Anchor a new fact, code convention, project invariant, or personal memory to your encrypted vault.

Input parameters:

- `content` (string, required): The fact, note, or invariant content to persist.
- `namespace` (string): Logical grouping for this memory (default: "default").

### `update_memory_vault` (~70 tokens)

Persist or supersede a personal fact, commitment, or preference in your encrypted Exogram memory vault.

Input parameters:

- `content` (string, required): The fact, preference, or commitment to persist.
- `namespace` (string): Logical grouping or sphere ("work", "household", "personal", or "default").

### `get_neural_cluster` (~62 tokens)

Look up an entity in Exogram's Layer 2 Knowledge Graph. Returns connected entities and directional relationships.

Input parameters:

- `entity_name` (string, required): Name of the entity to look up (e.g., "Next.js", "PostgreSQL", "SQLite WAL").

### `list_entities` (~37 tokens)

Retrieve active entities and concepts mapped in the personal knowledge network.

Input parameters:

- `limit` (number): Maximum number of entities to return (default 25).

### `check_action_safety` (~64 tokens)

Verify whether an agent action is safe and complies with active execution invariants before running.

Input parameters:

- `action` (string, required): The action name (e.g. "sql_execute", "file_delete", "api_call").
- `params` (object): Parameters supplied to the action.

### `record_decision` (~64 tokens)

Record an execution decision into the tamper-evident cryptographic audit ledger.

Input parameters:

- `action` (string, required): Action name.
- `decision` (string, required): Action decision.
- `params` (object): Parameters supplied.
- `reason` (string): Justification for the decision.

### `verify_audit_trail` (~29 tokens)

Verify the cryptographic SHA-256 hash chain integrity of the ledger from genesis to head.

### `query_graph` (~87 tokens)

Ask a natural language question against the knowledge graph and receive a structured answer with entity paths and gap analysis.

Input parameters:

- `max_hops` (number): Maximum traversal depth (1-4, default 2).
- `query` (string, required): The natural language question to ask, e.g. "How is Governed Autonomy connected to Exogram?" or "What do I know about AI safety?"

### `gmail_search_messages` (~78 tokens)

Search personal or workspace emails via Gmail API with query syntax (read-only).

Input parameters:

- `max_results` (number): Maximum number of messages to return (1-20, default 5).
- `query` (string, required): Search query using Gmail syntax (e.g., "from:xAI compute", "is:unread", "subject:launch").

### `gmail_create_draft` (~76 tokens)

Create an email draft in Gmail. Does NOT send the email without explicit user confirmation.

Input parameters:

- `body` (string, required): Body content (plain text or markdown).
- `cc` (string): Optional CC recipient email address.
- `subject` (string, required): Subject line of the draft email.
- `to` (string, required): Recipient email address.

### `drive_search_files` (~68 tokens)

Search documents, presentations, and files in Google Drive (read-only).

Input parameters:

- `max_results` (number): Maximum files to return (1-20, default 5).
- `query` (string, required): Search terms or MIME filters (e.g., "xAI compute", "type:presentation").

### `drive_create_presentation` (~43 tokens)

Create a new Google Slides presentation draft with structured slides.

Input parameters:

- `slides` (array, required): Array of slide definitions.
- `title` (string, required): Title of the presentation.

### `calendar_list_events` (~76 tokens)

List upcoming meetings, agenda items, and schedule availability from Google Calendar (read-only).

Input parameters:

- `max_results` (number): Maximum number of events to return (1-20, default 5).
- `query` (string): Search query or event keyword (e.g., "xAI sync", "Migration", "Team standup").

### `calendar_create_meeting` (~125 tokens)

Draft a new Google Calendar meeting invite. Does NOT send invites without explicit user confirmation.

Input parameters:

- `attendees` (array): List of attendee email addresses.
- `description` (string): Meeting agenda or description.
- `end_time` (string, required): ISO-8601 end timestamp (e.g., "2026-09-17T14:45:00Z").
- `start_time` (string, required): ISO-8601 start timestamp (e.g., "2026-09-17T14:00:00Z").
- `title` (string, required): Meeting title or summary.

### `github_search_issues` (~76 tokens)

Search issues and pull requests across connected GitHub repositories (read-only).

Input parameters:

- `query` (string, required): Search term or query syntax (e.g., "is:open label:bug", "cluster sync").
- `repo` (string): Repository in format "owner/repo" (e.g., "Richard-Ewing/exogram").

### `github_create_pr_draft` (~95 tokens)

Draft a GitHub Pull Request proposal. Does NOT open or publish the PR without explicit user approval.

Input parameters:

- `base` (string): Target base branch (default: "main").
- `body` (string, required): Detailed PR description and change summary.
- `head` (string, required): Feature or working branch name.
- `repo` (string, required): Repository in format "owner/repo".
- `title` (string, required): Pull request title.

### `notion_search_pages` (~54 tokens)

Search pages and databases in the user connected Notion workspace.

Input parameters:

- `filter_type` (string): Optional filter: "page" or "database".
- `query` (string, required): Search keywords or topic to find in Notion.

### `notion_append_block` (~84 tokens)

Draft new content or notes to append into an existing Notion page. Gated by explicit user approval.

Input parameters:

- `block_type` (string): Type of block: "paragraph", "bulleted_list_item", or "callout".
- `content` (string, required): Markdown content or structured notes to append.
- `page_id` (string, required): Target Notion page identifier or title.

### `slack_list_channels` (~39 tokens)

List accessible channels in the connected Slack workspace.

Input parameters:

- `types` (string): Channel types to list (e.g. "public_channel,private_channel").

### `slack_post_message_draft` (~75 tokens)

Draft a message to a Slack channel. Does NOT post without explicit user approval.

Input parameters:

- `channel` (string, required): Target channel name or ID (e.g. "#general", "#engineering").
- `message` (string, required): Message body or announcement content.
- `thread_ts` (string): Optional parent thread timestamp for threaded replies.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/richard-ewing-exogram/api#diagnostics

## Score history

- 2026-11-05: 71
- 2026-11-04: 71
- 2026-11-03: 70
- 2026-11-02: 70
- 2026-11-01: 69
- 2026-10-31: 69
- 2026-10-30: 68
- 2026-10-29: 68

## Common questions

### What is the Exogram — Personal AI Agent & Workspace MCP server?

Exogram — Personal AI Agent & Workspace is an MCP server listed in the public MCP registry as io.github.Richard-Ewing/exogram. Official MCP bridge to Exogram, the Personal AI Agent for your work, people, and life. This page covers its hosted endpoint (https://api.exogram.ai/mcp).

### Is the Exogram — Personal AI Agent & Workspace MCP server safe to use?

Exogram — Personal AI Agent & Workspace scores 71 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Exogram — Personal AI Agent & Workspace MCP server expose?

Exogram — Personal AI Agent & Workspace exposes 22 tools: search_vault, search_memory_vault, store_memory, update_memory_vault, get_neural_cluster, and 17 more. Their descriptions and schemas cost roughly 1,505 tokens of context every time the server is loaded.

### Does the Exogram — Personal AI Agent & Workspace MCP server require authentication?

No. We connected to Exogram — Personal AI Agent & Workspace without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Exogram — Personal AI Agent & Workspace MCP server still maintained?

Exogram — Personal AI Agent & Workspace is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://api.exogram.ai/mcp
- Repository: https://github.com/Richard-Ewing/exogram-sdk
- Website: https://exogram.ai/
- Changelog RSS feed: https://verifymcp.io/servers/richard-ewing-exogram/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/richard-ewing-exogram/api.json
- HTML version of this page: https://verifymcp.io/servers/richard-ewing-exogram/api