# Fraise (oci · ghcr.io/fraisehq/fraise)

Memory database for AI agents: remember and recall over a running Fraise daemon, in FQL.

- Trust score: 58/100 (low)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- oci · `ghcr.io/fraisehq/fraise`: 58/100 (this document), [markdown](https://verifymcp.io/servers/fraisehq-fraise/ghcr-io-fraisehq-fraise.md), [page](https://verifymcp.io/servers/fraisehq-fraise/ghcr-io-fraisehq-fraise)

## Channel facts

- Registry: `oci`
- Package: `ghcr.io/fraisehq/fraise`
- Version: `0.3.7`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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.

- **Supply Chain Security**: 0/100
  - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  - Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
  - Install-script risk not yet assessed.
  - Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to FraiseHQ/fraise).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 4 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 64/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 497 tokens (~248/item across 2 items; 2 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 60/100
  - Stability observed for 18 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 (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 2 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 2 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the Fraise MCP server?

Fraise runs locally as a container image, launched with docker run --rm -i ghcr.io/fraisehq/fraise:0.3.7. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add fraisehq-fraise -- docker run --rm -i ghcr.io/fraisehq/fraise:0.3.7
```

### Cursor

```json
{
  "mcpServers": {
    "fraisehq-fraise": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/fraisehq/fraise:0.3.7"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "fraisehq-fraise": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/fraisehq/fraise:0.3.7"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add fraisehq-fraise -- docker run --rm -i ghcr.io/fraisehq/fraise:0.3.7
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "fraisehq-fraise": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "ghcr.io/fraisehq/fraise:0.3.7"
      ],
      "enabled": true
    }
  }
}
```

### Hermes

```yaml
mcp_servers:
  fraisehq-fraise:
    command: "docker"
    args: ["run", "--rm", "-i", "ghcr.io/fraisehq/fraise:0.3.7"]
```

### Netclaw

```json
{
  "McpServers": {
    "fraisehq-fraise": {
      "Transport": "stdio",
      "Command": "docker",
      "Arguments": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/fraisehq/fraise:0.3.7"
      ]
    }
  }
}
```

### Other

```json
{
  "mcpServers": {
    "fraisehq-fraise": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/fraisehq/fraise:0.3.7"
      ]
    }
  }
}
```

## 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 58, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 57, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 56, 0)

- [functional] Package version: 0.3.5 → 0.3.6

### 2026-10-31 (score 56, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 55, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 54, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 53, 0)

- [security regression] Stability: 0.20 → unverified
- [security regression] Tool safety: pass → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified
- [functional] Package version: 0.3.4 → 0.3.5

### 2026-10-24 (score 53, +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.

## MCP tools (2)

### `recall` (~358 tokens)

Search the agent's long-term memory: run an FQL recall against the fraise daemon and return the matching facts ranked by relevance and recency. Anchors alone — topic:/entity: with no search terms and no vector — seed the search with every fact filed under them, scored one unit per named anchor and decayed by age, newest first under a single anchor: the way to see what is stored under a topic before you know what to search for.

Input parameters:

- `parameters` (object): Out-of-band vector bindings: one array of numbers per vec:$name placeholder the query references.
- `query` (string, required): A full FQL recall: search terms, then optional topic:/entity: anchors (beside terms they lift the facts filed under them through the graph and filter nothing, so the recall runs at depth:1 at least),…

Output parameters:

- `results` (object): Ranked recall results, best first; with anchors alone, each hit scores one unit per named anchor it is filed under, decayed by age — newest first under a single anchor.
- `warnings` (array): Parse warnings the server attached; the query still ran and the results stand.

### `remember` (~139 tokens)

Store a self-contained fact in the agent's long-term memory: run an FQL remember against the fraise daemon.

Input parameters:

- `parameters` (object): Out-of-band vector bindings: one array of numbers per vec:$name placeholder the query references.
- `query` (string, required): A full FQL remember: the fact in single quotes, anchors as repeatable topic:/entity: pairs, @N selecting the graph, vec:$name binding an optional vector. An anchor value that is not letters and digit…

Output parameters:

- `status` (string): The write acknowledgement, the fixed token "ok". A write has no result set to return; this key's presence is what distinguishes an accepted write from a recall that matched nothing.
- `warnings` (array): Parse warnings the server attached; the query still ran and the results stand.

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/fraisehq-fraise/ghcr-io-fraisehq-fraise#diagnostics

## Score history

- 2026-11-05: 58
- 2026-11-04: 58
- 2026-11-03: 57
- 2026-11-02: 57
- 2026-11-01: 56
- 2026-10-31: 56
- 2026-10-30: 55
- 2026-10-29: 55
- 2026-10-28: 54
- 2026-10-27: 54
- 2026-10-26: 53
- 2026-10-25: 53
- 2026-10-24: 53
- 2026-10-23: 52
- 2026-10-22: 52
- 2026-10-21: 51
- 2026-10-20: 51
- 2026-10-19: 50
- 2026-10-18: 50

## Common questions

### What is the Fraise MCP server?

Fraise is an MCP server listed in the public MCP registry as io.github.FraiseHQ/fraise. Memory database for AI agents: remember and recall over a running Fraise daemon, in FQL. This page covers its container image (ghcr.io/fraisehq/fraise).

### Is the Fraise MCP server safe to use?

Fraise scores 58 out of 100 on VerifyMCP. Its build provenance is signed and verified. 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 Fraise MCP server expose?

Fraise exposes 2 tools: recall, remember. Their descriptions and schemas cost roughly 497 tokens of context every time the server is loaded.

### Is the Fraise MCP server still maintained?

Fraise 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.

### What licence is the Fraise MCP server under?

Fraise declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- GitHub Container Registry: https://ghcr.io/fraisehq/fraise
- Repository: https://github.com/FraiseHQ/fraise
- Website: https://docs.getfraise.dev/
- Changelog RSS feed: https://verifymcp.io/servers/fraisehq-fraise/ghcr-io-fraisehq-fraise.xml
- Changelog JSON feed: https://verifymcp.io/servers/fraisehq-fraise/ghcr-io-fraisehq-fraise.json
- HTML version of this page: https://verifymcp.io/servers/fraisehq-fraise/ghcr-io-fraisehq-fraise