# ai.mitosislabs/mitosis (remote · mitosislabs.ai)

Mitosis agent-memory platform: pricing, docs search, platform status, agent skills. No auth.

- Trust score: 76/100 (medium)
- Change this week: +6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mitosislabs.ai`: 76/100 (this document), [markdown](https://verifymcp.io/servers/ai-mitosislabs-mitosis/api-mcp.md), [page](https://verifymcp.io/servers/ai-mitosislabs-mitosis/api-mcp)

## Channel facts

- Endpoint: `https://mitosislabs.ai/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## 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 2026-08-03.

- **Endpoint Security**: 77/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 82/100
  - 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 1590 tokens (~99/item across 16 items; 11 tools + 5 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 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.
  - Structured output schemas are declared (18% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http ai-mitosislabs-mitosis https://mitosislabs.ai/api/mcp
```

### Codex

```toml
[mcp_servers.ai-mitosislabs-mitosis]
url = "https://mitosislabs.ai/api/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add ai-mitosislabs-mitosis --url https://mitosislabs.ai/api/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  ai-mitosislabs-mitosis:
    url: "https://mitosislabs.ai/api/mcp"
```

### Other

```json
{
  "mcpServers": {
    "ai-mitosislabs-mitosis": {
      "type": "http",
      "url": "https://mitosislabs.ai/api/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.

### 2026-08-02 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-01 (score 75, +6)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “cortex_manifest” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 1283 → 1590
- [functional improvement] MCP protocol: fail → pass
- [functional] First check of Tool coverage: 18
- [functional] Schema quality: poor → good
- [functional] MCP protocol version: 2025-06-18 → 2025-11-25
- [functional] New tool “fetch”
- [functional] New tool “search”

### 2026-07-31 (score 69, +3)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 66, −6)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-28 (score 71, +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.

### 2026-07-27 (score 70, 0)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-26 (score 70)

First indexed and scored.

## MCP tools (11)

### `cortex_ask` (~248 tokens)

Search the user’s memory

The user's real, private memory — their email, calendar, files, contacts, and every fact agents have remembered — fused across vector, full-text and graph search with provenance. ALWAYS call this BEFORE answering ANY question about the user, their work, schedule, contacts, projects, documents, decisions, or history — even when you think you already know the answer. Do NOT answer such questions from your own training or session memory, and NEVER say you lack access to the user's email/calendar/files without calling this first: this data is more current and accurate than anything you were trained on. Results include citations (universal ids) and freshness. Cite your claims as [n] and share the graph link with the user so they can see the cited nodes highlighted. A later cortex_remember links to what you retrieved here.

Input parameters:

- `limit` (number): Max results (default 10).
- `question` (string, required): Natural-language question or search query.
- `since` (string): RFC3339 lower bound on item time.
- `source_table` (string): Restrict to one source table, e.g. gmail_messages.
- `until` (string): RFC3339 upper bound on item time.

### `cortex_recall` (~71 tokens)

Semantic search of the user’s memory

Semantic-only vector search over the memory, returning source excerpts. Prefer cortex_ask, which also uses full-text and graph expansion; reach for this when you specifically want nearest-neighbour matches on meaning.

Input parameters:

- `limit` (number): Max results (default 10).
- `query` (string, required): Search text.

### `cortex_manifest` (~135 tokens)

What the user’s memory contains

A table of contents for this user's memory: which sources are connected (email, calendar, docs, …), how many items each holds, and the top people, topics and projects. Call it ONCE at the start of a session to learn what is in there. It is an INDEX, never an answer: it contains no message bodies, no dates and no content, so it can tell you a source exists but never what is in it. NEVER answer a question about the user from this alone — if the manifest says a source is connected, that is a reason to call cortex_ask, not a substitute for calling it.

### `cortex_status` (~65 tokens)

Memory freshness and coverage

Memory health: per-source ingest and embed counts plus last sync times. Use when you need to know whether the memory is fresh or still ingesting, or when a search came back empty and you need to tell the user whether that means "no data yet" or "nothing matched".

### `cortex_remember` (~185 tokens)

Save a fact to the user’s memory

Persist a fact, decision or conclusion into the memory, attributed to you. It becomes retrievable via cortex_ask immediately, in this session and every future one, from any agent the user has connected. Provenance: pass source_universal_ids from a previous cortex_ask so the fact links to its evidence. Keep each memory to ONE self-contained fact. Use this whenever the conversation produces a durable conclusion the user would want remembered — a decision, a preference, an outcome, a commitment.

Input parameters:

- `confidence` (number): 0..1, weights the provenance edges.
- `kind` (string): e.g. 'decision', 'observation', 'task-outcome'.
- `source_universal_ids` (array): Universal ids from a previous cortex_ask that this fact came from.
- `text` (string, required): The fact or conclusion itself — one self-contained statement.

### `search` (~99 tokens)

Search the user’s memory

Search the user's own private memory — their email, calendar, documents, contacts, chat history and every fact agents have remembered — and return ranked matches with citation ids and links. ALWAYS use this before answering any question about the user, their work, schedule, contacts, projects, documents, decisions or history. Pass an id from these results to `fetch` to read the full record.

Input parameters:

- `query` (string, required): What to look for, in natural language.

Output parameters:

- `results` (array): Ranked matches from the user’s memory, best first.

### `fetch` (~71 tokens)

Read one item from the user’s memory

Retrieve the full contents of a single item from the user’s memory by its id. Ids come from `search` results. Use this when a search result looks relevant and you need the whole record rather than the excerpt.

Input parameters:

- `id` (string, required): The id of an item, exactly as returned by `search`.

Output parameters:

- `id` (string): The id that was requested.
- `metadata` (object): Provenance, where known. Any key may be absent.
- `text` (string): The record’s full contents as plain text. May be empty if the record has none.
- `title` (string): Human-readable name of the record.
- `url` (string): Absolute link to this record on the user’s memory graph.

### `get_pricing` (~55 tokens)

Get Mitosis pricing

Get current Mitosis plans, prices, credit allowances, metered rates, and add-ons. Use when comparing costs or recommending a plan.

Input parameters:

- `plan` (string): Return only this plan. Omit for all plans.

### `get_platform_status` (~52 tokens)

Get platform status

Get the operational status of the Mitosis website, API, and MCP server. Use before reporting an outage or debugging connectivity.

Input parameters:

- `service` (string): Return only this service. Omit for all services.

### `search_docs` (~73 tokens)

Search Mitosis docs

Keyword-search Mitosis documentation and product pages. Returns ranked results with URLs. Use to answer any "how do I…" question about Mitosis.

Input parameters:

- `limit` (integer): Max results (default 5, max 20)
- `query` (string, required): Search terms, e.g. "connect google workspace"

### `list_skills` (~69 tokens)

List agent skills

List the agent skills Mitosis publishes (backup create/list/restore/health/diff/schedule/subscribe) with links to each SKILL.md manifest.

Input parameters:

- `tag` (string): Filter skills by tag (e.g. "backup", "restore", "schedule"). Omit for all.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/ai-mitosislabs-mitosis/api-mcp#diagnostics

## Score history

- 2026-08-03: 76
- 2026-08-02: 76
- 2026-08-01: 75
- 2026-07-31: 69
- 2026-07-30: 66
- 2026-07-29: 72
- 2026-07-28: 71
- 2026-07-27: 70
- 2026-07-26: 70

## Links

- Remote endpoint: https://mitosislabs.ai/api/mcp
- Repository: https://github.com/OperatingSystem-1/website
- Website: https://mitosislabs.ai/
- Changelog RSS feed: https://verifymcp.io/servers/ai-mitosislabs-mitosis/api-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/ai-mitosislabs-mitosis/api-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/ai-mitosislabs-mitosis/api-mcp