# io.github.Savirinc/unfragile (remote · unfragile.ai)

Find the AI infrastructure or agent tool for a task, labelled by our checks, with signed receipts.

- Trust score: 72/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `unfragile.ai`: 72/100 (this document), [markdown](https://verifymcp.io/servers/savirinc-unfragile/api-mcp.md), [page](https://verifymcp.io/servers/savirinc-unfragile/api-mcp)
- npm · `@unfragile/mcp-server`: 64/100, [markdown](https://verifymcp.io/servers/savirinc-unfragile/unfragile-mcp-server.md), [page](https://verifymcp.io/servers/savirinc-unfragile/unfragile-mcp-server)

## Channel facts

- Endpoint: `https://unfragile.ai/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.13.0`

## 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 2026-11-21.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - 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**: 63/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 735 tokens (~183/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 3/100
  - Stability observed for 1 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 4 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 5 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 io.github.Savirinc/unfragile MCP server?

io.github.Savirinc/unfragile is a hosted endpoint at https://unfragile.ai/api/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 savirinc-unfragile 'https://unfragile.ai/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "savirinc-unfragile": {
      "url": "https://unfragile.ai/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "savirinc-unfragile": {
      "type": "http",
      "url": "https://unfragile.ai/api/mcp"
    }
  }
}
```

### Codex

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

### opencode

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

### OpenClaw

```bash
openclaw mcp add savirinc-unfragile --url 'https://unfragile.ai/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  savirinc-unfragile:
    url: "https://unfragile.ai/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "savirinc-unfragile": {
      "Transport": "http",
      "Url": "https://unfragile.ai/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add savirinc-unfragile -t streamable-http -u 'https://unfragile.ai/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "savirinc-unfragile": {
      "type": "http",
      "url": "https://unfragile.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.

### 2026-11-21 (score 72, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-20 (score 71)

First indexed and scored.

## MCP tools (4)

### `unfragile_find` (~429 tokens)

Find the AI infrastructure or tool action for a task

Finds the product, and the specific tool action, that does a task, across AI infrastructure (search APIs, models, inference, browsers, harnesses, compute) and the MCP servers, APIs, CLIs, SDKs and models in our index. Each result carries the label from our checks (verified and signed · official · checked: not enough evidence yet · found in code, not yet checked · demo or tutorial · failed its last check) and a signed receipt. answer: true adds a written, cited answer; false returns the ranked list. A fact we hold (a price, a limit, a model id) arrives in structuredContent.blocks (type 'fact') and at the start of the answer, never in results.

Input parameters:

- `answer` (boolean): Also return a written answer: the products that do it, each cited to its maker's own pages. Default here: true (this door has always answered); false lists the products without writing
- `client_model` (string): The model that will read the answer (recorded on the receipt)
- `intent` (string): Deprecated: the old name of `kind` (kept so 0.10 callers work)
- `kind` (string): With search: 'product' (which product does X), 'action' (the one operation to call) or 'model' (which AI model)
- `lane` (string): fast: ranked results only · standard: results and a written, cited answer (default) · best: a freshly written answer
- `limit` (integer): How many results (default 5)
- `max_age` (integer): Seconds: a remembered answer older than this is written afresh
- `named` (array): With search: products the task names, so they lead
- `search` (string): Optional: your own 3-10 word search phrase; skips our reading step
- `session_id` (string): Your own id for this task (recorded on the receipt)
- `task` (string, required): What you need done, in plain words

### `unfragile_verify` (~101 tokens)

Verify a tool, MCP server or package before invoking it

Returns our verdict on a tool, MCP server or package (trusted · caution · unverified · flagged) and the reason, with its Ed25519-signed passport, checkable offline against https://unfragile.ai/api/v1/trust-passport-public-key. A flagged verdict means it failed our checks.

Input parameters:

- `target` (string, required): Target identity, e.g. 'npm:@stripe/mcp', a package name, or a record id

### `unfragile_resolve` (~64 tokens)

Resolve one task to one checked record

Returns one checked record for a task, with its verdict, its Ed25519-signed passport and a paste-ready install line, or says that nothing qualifies.

Input parameters:

- `intent` (string, required): The task, e.g. 'send a slack message from an agent'

### `unfragile_passport` (~72 tokens)

Fetch a record's signed trust passport

Fetch the raw Ed25519-signed trust passport JSON for a record (by record page slug, record id, or npm package). For programmatic policy checks; verify offline against the published public key.

Input parameters:

- `slug` (string, required): Record page slug, record id (npm:…), or package name

## Diagnostics

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

## Score history

- 2026-11-21: 72
- 2026-11-20: 71

## Common questions

### What is the io.github.Savirinc/unfragile MCP server?

io.github.Savirinc/unfragile is an MCP server listed in the public MCP registry as io.github.Savirinc/unfragile. Find the AI infrastructure or agent tool for a task, labelled by our checks, with signed receipts. This page covers its hosted endpoint (https://unfragile.ai/api/mcp).

### Is the io.github.Savirinc/unfragile MCP server safe to use?

io.github.Savirinc/unfragile scores 72 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 io.github.Savirinc/unfragile MCP server expose?

io.github.Savirinc/unfragile exposes 4 tools: unfragile_find, unfragile_verify, unfragile_resolve, unfragile_passport. Their descriptions and schemas cost roughly 666 tokens of context every time the server is loaded.

### Does the io.github.Savirinc/unfragile MCP server require authentication?

No. We connected to io.github.Savirinc/unfragile without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the io.github.Savirinc/unfragile MCP server still maintained?

io.github.Savirinc/unfragile is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the io.github.Savirinc/unfragile MCP server?

VerifyMCP ran 13 checks on io.github.Savirinc/unfragile, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://unfragile.ai/api/mcp
- Repository: https://github.com/Savirinc/unfragile-mcp-server
- Changelog RSS feed: https://verifymcp.io/servers/savirinc-unfragile/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/savirinc-unfragile/api-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/savirinc-unfragile/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/savirinc-unfragile/api-mcp
