# io.github.BlueprintLabIO/tidebase (npm · @tidebase/mcp)

Inspect Tidebase agent runs, resolve approval gates, and trigger recovery from your AI assistant.

- Trust score: 70/100 (medium)
- Change this week: +44
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@tidebase/mcp`: 70/100 (this document), [markdown](https://verifymcp.io/servers/blueprintlabio-tidebase/tidebase-mcp.md), [page](https://verifymcp.io/servers/blueprintlabio-tidebase/tidebase-mcp)

## Channel facts

- Registry: `npm`
- Package: `@tidebase/mcp`
- Version: `0.1.1`
- 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 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 51 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 77/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 595 tokens (~85/item across 7 items; 7 tools + 0 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.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add blueprintlabio-tidebase -- npx -y @tidebase/mcp
```

### Codex

```bash
codex mcp add blueprintlabio-tidebase -- npx -y @tidebase/mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "blueprintlabio-tidebase": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@tidebase/mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add blueprintlabio-tidebase --command npx --arg -y --arg @tidebase/mcp
```

### Hermes

```yaml
mcp_servers:
  blueprintlabio-tidebase:
    command: "npx"
    args: ["-y", "@tidebase/mcp"]
```

### Other

```json
{
  "mcpServers": {
    "blueprintlabio-tidebase": {
      "command": "npx",
      "args": [
        "-y",
        "@tidebase/mcp"
      ]
    }
  }
}
```

## 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.

### 2026-08-03 (score 70, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-08-02 (score 66, +30)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] License: unverified → pass
- [functional] Licence: Apache-2.0

### 2026-08-01 (score 36, +31)

- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass

### 2026-07-31 (score 5, −57)

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

### 2026-07-30 (score 62, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-28 (score 80, +54)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] License: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Tool coverage: 100
- [functional] First check of Schema quality: pass
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: excellent
- [functional] Licence: Apache-2.0

### 2026-07-27 (score 26)

First indexed and scored.

## MCP tools (7)

### `tidebase_health` (~36 tokens)

Check Tidebase server health

Verify the Tidebase server is reachable. Use this first if other tools fail. Configured server: http://localhost:7373

### `tidebase_list_runs` (~52 tokens)

List recent runs

List the 100 most recent Tidebase runs with workflow name, status, attempt count, and timestamps. Use to find a run id or get an overview of what is running, failed, or awaiting review.

### `tidebase_get_run` (~101 tokens)

Get full run detail

Fetch everything Tidebase knows about one run: the run record, checkpointed steps (with resume contracts and failure classification), live state, versioned state streams, parent/child run edges, gates, recovery attempts, channel deliveries, usage records, and the append-only event log. Use to answer "where did this run stop and is it safe to rerun?"

Input parameters:

- `runId` (string, required): Run id, e.g. run_abc123

### `tidebase_create_run` (~112 tokens)

Create a run

Create a new Tidebase run row for a workflow. Note: Tidebase does not execute code — creating a run registers it (with optional input, recovery webhook, and channels); your application must invoke the workflow function with this run id for steps to execute.

Input parameters:

- `input`: Workflow input, stored with the run
- `recoveryWebhook` (string): URL Tidebase calls with a signed run.resume payload when the run fails
- `workflowName` (string, required): Workflow name, e.g. generate-report

### `tidebase_get_state_versions` (~90 tokens)

Get state version history

Read the versioned state history of a run. A snapshot is a labeled state version; time travel is reading an older version. Filter to one stream or to labeled versions (snapshots) only.

Input parameters:

- `labeledOnly` (boolean): Return only labeled versions (snapshots)
- `runId` (string, required): Run id
- `stream` (string): Limit to one state stream by name

### `tidebase_resolve_gate` (~136 tokens)

Resolve an approval gate

Approve, reject, or cancel a pending human-approval gate. Requires the gate resolveToken (found in the gate record via tidebase_get_run, or in the gate.created webhook payload). Gates resolve exactly once: a second attempt returns a conflict. Only resolve a gate when the human you are assisting has explicitly made the decision.

Input parameters:

- `actor` (string): Who decided, for the audit record
- `decision` (string, required): The decision
- `gateId` (string, required): Gate id
- `runId` (string, required): Run id the gate belongs to
- `token` (string, required): The gate resolveToken

### `tidebase_trigger_recovery` (~68 tokens)

Trigger run recovery

Ask Tidebase to dispatch the run's recovery webhook so the owning application re-invokes the workflow. Completed steps replay from checkpoints; only unfinished steps execute. Has no effect unless the run was created with a recoveryWebhook.

Input parameters:

- `runId` (string, required): Run id to recover

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/blueprintlabio-tidebase/tidebase-mcp#diagnostics

## Score history

- 2026-08-03: 70
- 2026-08-02: 66
- 2026-08-01: 36
- 2026-07-31: 5
- 2026-07-30: 62
- 2026-07-29: 80
- 2026-07-28: 80
- 2026-07-27: 26

## Links

- npm package: https://www.npmjs.com/package/@tidebase/mcp
- Socket report: https://socket.dev/npm/package/@tidebase/mcp
- Repository: https://github.com/BlueprintLabIO/tidebase
- Website: https://tidebase.dev/
- Changelog RSS feed: https://verifymcp.io/servers/blueprintlabio-tidebase/tidebase-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/blueprintlabio-tidebase/tidebase-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/blueprintlabio-tidebase/tidebase-mcp