# Moltline Recall (remote · mcp.moltlinestudio.com)

A portable knowledge-graph memory you pass in and get back. No database. 4 of 6 free.

- Trust score: 87/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-21

## Components

- remote · `mcp.moltlinestudio.com`: 87/100 (this document), [markdown](https://verifymcp.io/servers/com-moltlinestudio-recall/recall.md), [page](https://verifymcp.io/servers/com-moltlinestudio-recall/recall)

## Channel facts

- Endpoint: `https://mcp.moltlinestudio.com/recall`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.2.0`

## 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 2026-09-21.

- **Endpoint Security**: 83/100
  - 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.
  - The HSTS (Strict-Transport-Security) header is present.
  - 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**: 63/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1893 tokens (~315/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **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 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 7 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 Moltline Recall MCP server?

Moltline Recall is a hosted endpoint at https://mcp.moltlinestudio.com/recall, 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 com-moltlinestudio-recall 'https://mcp.moltlinestudio.com/recall'
```

### Cursor

```json
{
  "mcpServers": {
    "com-moltlinestudio-recall": {
      "url": "https://mcp.moltlinestudio.com/recall"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-moltlinestudio-recall": {
      "type": "http",
      "url": "https://mcp.moltlinestudio.com/recall"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-moltlinestudio-recall]
url = "https://mcp.moltlinestudio.com/recall"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-moltlinestudio-recall": {
      "type": "remote",
      "url": "https://mcp.moltlinestudio.com/recall",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-moltlinestudio-recall --url 'https://mcp.moltlinestudio.com/recall' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-moltlinestudio-recall:
    url: "https://mcp.moltlinestudio.com/recall"
```

### Netclaw

```json
{
  "McpServers": {
    "com-moltlinestudio-recall": {
      "Transport": "http",
      "Url": "https://mcp.moltlinestudio.com/recall"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-moltlinestudio-recall -t streamable-http -u 'https://mcp.moltlinestudio.com/recall'
```

### Other

```json
{
  "mcpServers": {
    "com-moltlinestudio-recall": {
      "type": "http",
      "url": "https://mcp.moltlinestudio.com/recall"
    }
  }
}
```

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.

### 2026-09-19 (score 87, +1)

- [security] Stability: 0.97 → pass

### 2026-09-17 (score 86, +1)

No change was recorded against any check on this day. Stability & Change Management went from 90 to 93. That category is still filling its 30-day observation window: 27 days of observed history at the previous scan, 28 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-15 (score 85, +1)

No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-13 (score 84, +1)

No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-11 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-09 (score 82, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-09-06 (score 81, +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.

### 2026-09-04 (score 80, +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.

## MCP tools (6)

### `graph_upsert` (~389 tokens)

Graph Upsert

Fold new facts into a memory graph and get the whole graph back. FREE.

Idempotent by construction: re-adding the same entity, observation or
relation changes nothing, so an agent that replays its own history does not
end up with a graph full of duplicates. Typical input {"graph": {"entities":
[], "relations": []}, "entities": [{"name": "Acme Corp", "type":
"company", "observations": ["renewed in March"]}]} returns {"graph": {...},
"added": {"entities": 1, "observations": 1, "relations": 0}, "merged": 0}.

Use as the single write path for memory. Not for reading it back
selectively - that is graph_search - and not for finding out what a write
changed, which graph_diff answers precisely. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "graph exceeds <value> entities; split it"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

Input parameters:

- `entities`: Entities to add or extend, each {"name": ..., "type": ..., "observations": [...]}. Observations are appended and deduplicated; an existing entity keeps its type unless a new one is supplied.
- `graph`: The existing graph document, or omitted to start a new one. Shape: {"entities": [...], "relations": [...]}.
- `relations`: Relations to add, each {"from": ..., "to": ..., "type": ..., and optionally "since", "until", "confidence"}. Dates are ISO 8601 (YYYY-MM-DD); confidence is 0 to 1.

### `graph_search` (~361 tokens)

Graph Search

Find what the graph knows about something, plus its neighbourhood. FREE.

Scores entities by how many query words appear in the name, type and
observations, then pulls in whatever is within the requested number of
hops - because the useful answer to "what do we know about Acme" is
usually Acme plus who it is connected to. Typical input {"graph": {...},
"query": "acme renewal", "hops": 1} returns {"matches": [{"name": "Acme
Corp", "score": 3, "why": ["name", "observation"]}], "neighbourhood":
{"entities": [...], "relations": [...]}, "hops": 1}.

Use to read memory back before answering. Not for writing (graph_upsert)
and not for narrowing by date, which graph_at_time does. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "query must contain at least one word or number"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

Input parameters:

- `graph` (object, required): The graph document to search.
- `hops` (integer): How far to expand from each match along relations. 0 returns matches only; 3 is the maximum. Default 1.
- `limit` (integer): Maximum entities to return. Default 20, maximum 200.
- `query` (string, required): Words to look for, e.g. "acme renewal". Matching is on whole lowercase words, so it is exact and repeatable rather than fuzzy.

### `graph_diff` (~215 tokens)

Graph Diff

Say exactly what changed between two versions of a memory. FREE.

The audit trail a database gives you for free, without the database.
Typical input {"before": {...}, "after": {...}} returns
{"entities_added": ["Beta Ltd"], "entities_removed": [],
"observations_added": {"Acme Corp": ["renewed in March"]},
"relations_added": [...], "changed": true}.

Use after an upsert to record what a session learned, or between two
agents to see what one knows that the other does not. Not for merging the
two - feed the differences back through graph_upsert for that. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"}. Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

Input parameters:

- `after` (object, required): The later graph document.
- `before` (object, required): The earlier graph document.

### `graph_lint` (~239 tokens)

Graph Lint

Find the breaks a memory graph accumulates as it grows. FREE.

Relations pointing at entities that do not exist, entities nothing points
at, near-duplicate names, and observations that contradict each other on
the same entity. Typical input {"graph": {...}} returns {"ok": false,
"dangling_relations": [{"from": "Acme Corp", "to": "Beta Ltd", "missing":
["Beta Ltd"]}], "orphan_entities": ["Old Note"], "near_duplicates":
[["Acme Corp", "Acme  Corp."]], "contradictions": []}.

Use before trusting a graph you did not build, or on a schedule as memory
grows. Not for comparing two graphs (graph_diff) and not for shrinking one
(graph_compact). Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"}. Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

Input parameters:

- `graph` (object, required): The graph document to check.

### `graph_at_time` (~331 tokens)

Graph At Time

See the memory as it stood on a given day, optionally faded by age. PREMIUM (license).

Relations carrying since and until are filtered to those in force on the
date; with a half-life, confidence decays exponentially with age so a
two-year-old belief does not weigh the same as last week's. Typical input
{"graph": {...}, "as_of": "2026-06-01", "half_life_days": 180} returns
{"as_of": "2026-06-01", "graph": {...}, "dropped": {"not_yet": 1,
"expired": 2}, "decayed": 4}.

Use when the answer depends on when you ask. Not for what changed between
two points - that is graph_diff, which does not need dates at all. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"} (for example {"error": "as_of must be a date like 2026-06-01"}). Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

Input parameters:

- `as_of` (string, required): The date to view the memory as of, ISO 8601, e.g. "2026-06-01".
- `graph` (object, required): The graph document.
- `half_life_days` (integer): Days over which a relation's confidence halves. 0, the default, disables decay and leaves confidence untouched.

### `graph_compact` (~290 tokens)

Graph Compact

Shrink a memory to the part that still earns its place. PREMIUM (license).

Ranks entities by how connected they are and how much is recorded about
them, keeps anything you name outright, and drops the rest along with the
relations that pointed at them. Typical input {"graph": {...},
"max_entities": 50, "keep": ["Acme Corp"]} returns {"graph": {...},
"kept": 50, "dropped_entities": ["Old Note", ...], "dropped_relations": 12,
"ranking": "degree, then observation count, then name"}.

Use when a graph has outgrown the context you can spend on it. Not for
removing wrong facts - graph_lint finds those, and deleting them is a
decision you should make deliberately rather than by ranking. Errors: on invalid, missing, or malformed input this tool never raises a protocol error — it returns {"error": "<what is wrong and how to fix it>"}. Every call is read-only and idempotent, so after correcting the input it is always safe to retry.

Input parameters:

- `graph` (object, required): The graph document to compact.
- `keep`: Entity names to keep regardless of rank, e.g. ["Acme Corp"]. Matched case-insensitively.
- `max_entities` (integer): How many entities to keep. Default 50.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-moltlinestudio-recall/recall#diagnostics

## Score history

- 2026-09-21: 87
- 2026-09-20: 87
- 2026-09-19: 87
- 2026-09-18: 86
- 2026-09-17: 86
- 2026-09-16: 85
- 2026-09-15: 85
- 2026-09-14: 84
- 2026-09-13: 84
- 2026-09-12: 83
- 2026-09-11: 83
- 2026-09-10: 82
- 2026-09-09: 82
- 2026-09-08: 81
- 2026-09-07: 81
- 2026-09-06: 81
- 2026-09-05: 80
- 2026-09-04: 80
- 2026-09-03: 79
- 2026-09-02: 79
- 2026-09-01: 78
- 2026-08-31: 78
- 2026-08-30: 77
- 2026-08-29: 77
- 2026-08-28: 76
- 2026-08-27: 76
- 2026-08-26: 75
- 2026-08-25: 73
- 2026-08-24: 73
- 2026-08-23: 72

## Common questions

### What is the Moltline Recall MCP server?

Moltline Recall is an MCP server listed in the public MCP registry as com.moltlinestudio/recall. A portable knowledge-graph memory you pass in and get back. No database. 4 of 6 free. This page covers its hosted endpoint (https://mcp.moltlinestudio.com/recall).

### Is the Moltline Recall MCP server safe to use?

Moltline Recall scores 87 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 Moltline Recall MCP server expose?

Moltline Recall exposes 6 tools: graph_upsert, graph_search, graph_diff, graph_lint, graph_at_time, graph_compact. Their descriptions and schemas cost roughly 1,825 tokens of context every time the server is loaded.

### Does the Moltline Recall MCP server require authentication?

No. We connected to Moltline Recall without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Moltline Recall MCP server still maintained?

Moltline Recall is still listed as active in the MCP registry. We last reached this channel on 21 September 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://mcp.moltlinestudio.com/recall
- Repository: https://github.com/GarphenGate/moltline-mcp
- Website: https://moltlinestudio.com/servers.html#recall
- Changelog RSS feed: https://verifymcp.io/servers/com-moltlinestudio-recall/recall.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-moltlinestudio-recall/recall.json
- HTML version of this page: https://verifymcp.io/servers/com-moltlinestudio-recall/recall