Rank
83
A Model Context Protocol (MCP) server for GitLab
Traction
No public download signal
Freshness
Updated 2d ago
Crawler Summary
MCP server for controlling Lovense toys via the Lovense Cloud API lovense-mcp MCP server for controlling Lovense toys via the Lovense Cloud API. Runs on a home server, works from anywhere, lets your AI of choice take creative control. Built with TypeScript, Bun, Hono, and the MCP SDK. --- How it works **Why cloud and not LAN?** The Lovense Remote app is on your phone, outside your home network — not on the same LAN as your server. The Lovense Server API (cloud relay) is therefore m Capability contract not published. No trust telemetry is available yet. Last updated 2/25/2026.
Freshness
Last checked 2/25/2026
Best For
lovense-mcp is best for general automation workflows where MCP compatibility matters.
Not Ideal For
Contract metadata is missing or unavailable for deterministic execution.
Evidence Sources Checked
editorial-content, GITHUB MCP, runtime-metrics, public facts pack
MCP server for controlling Lovense toys via the Lovense Cloud API lovense-mcp MCP server for controlling Lovense toys via the Lovense Cloud API. Runs on a home server, works from anywhere, lets your AI of choice take creative control. Built with TypeScript, Bun, Hono, and the MCP SDK. --- How it works **Why cloud and not LAN?** The Lovense Remote app is on your phone, outside your home network — not on the same LAN as your server. The Lovense Server API (cloud relay) is therefore m
Public facts
4
Change events
1
Artifacts
0
Freshness
Feb 25, 2026
Capability contract not published. No trust telemetry is available yet. Last updated 2/25/2026.
Trust score
Unknown
Compatibility
MCP
Freshness
Feb 25, 2026
Vendor
Gradleless
Artifacts
0
Benchmarks
0
Last release
1.0.0
Key links, install path, and a quick operational read before the deeper crawl record.
Summary
Capability contract not published. No trust telemetry is available yet. Last updated 2/25/2026.
Setup snapshot
git clone https://github.com/Gradleless/lovense-mcp.gitSetup complexity is MEDIUM. Standard integration tests and API key provisioning are required before connecting this to production workloads.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.
Everything public we have scraped or crawled about this agent, grouped by evidence type with provenance.
Vendor
Gradleless
Protocol compatibility
MCP
Handshake status
UNKNOWN
Crawlable docs
6 indexed pages on the official domain
Merged public release, docs, artifact, benchmark, pricing, and trust refresh events.
Extracted files, examples, snippets, parameters, dependencies, permissions, and artifact metadata.
Extracted files
0
Examples
6
Snippets
0
Languages
typescript
text
You (outside, Claude Desktop or any MCP client)
↕ HTTP/SSE — MCP transport
Your home server (NAS, VPS…)
↕ HTTPS — Lovense Server API
Lovense Cloud
↕ Push
Lovense Remote App (your phone, also outside)
↕ Bluetooth
Your toysbash
git clone https://github.com/Gradleless/lovense-mcp cd lovense-mcp bun install
bash
cp env.example .env
bash
# Development (watch mode, pretty logs) bun run dev # Production bun run start
text
Setup page: http://localhost:3000/setup?token=your_token
text
Output: { toys: [...], lastSeenAt: "ISO date or null" }Full documentation captured from public sources, including the complete README when available.
Docs source
GITHUB MCP
Editorial quality
ready
MCP server for controlling Lovense toys via the Lovense Cloud API lovense-mcp MCP server for controlling Lovense toys via the Lovense Cloud API. Runs on a home server, works from anywhere, lets your AI of choice take creative control. Built with TypeScript, Bun, Hono, and the MCP SDK. --- How it works **Why cloud and not LAN?** The Lovense Remote app is on your phone, outside your home network — not on the same LAN as your server. The Lovense Server API (cloud relay) is therefore m
MCP server for controlling Lovense toys via the Lovense Cloud API. Runs on a home server, works from anywhere, lets your AI of choice take creative control.
Built with TypeScript, Bun, Hono, and the MCP SDK.
You (outside, Claude Desktop or any MCP client)
↕ HTTP/SSE — MCP transport
Your home server (NAS, VPS…)
↕ HTTPS — Lovense Server API
Lovense Cloud
↕ Push
Lovense Remote App (your phone, also outside)
↕ Bluetooth
Your toys
Why cloud and not LAN? The Lovense Remote app is on your phone, outside your home network — not on the same LAN as your server. The Lovense Server API (cloud relay) is therefore mandatory. Architecture fun, life complicated.
Why HTTP/SSE and not stdio? stdio requires the MCP server and the AI client to run on the same machine. Here the server is remote — hence HTTP/SSE transport.
Follow Lovense's official guide to:
https://your-server.example.com/callbackThe callback URL is the part everyone forgets. Without it, your server never hears from Lovense and nothing works. Don't skip this.
git clone https://github.com/Gradleless/lovense-mcp
cd lovense-mcp
bun install
cp env.example .env
See Configuration below for all variables.
# Development (watch mode, pretty logs)
bun run dev
# Production
bun run start
The server logs the setup URL on startup:
Setup page: http://localhost:3000/setup?token=your_token
Open the setup URL in a browser, scan the QR code with the Lovense Remote app. The app will call your /callback endpoint and register your toys. From this point on, the server receives periodic heartbeats (~every 10s) to track what's connected.
The QR code expires after 4 hours. Visit
/setupagain to get a new one.
Point any MCP-compatible client (Claude Desktop, Cursor, Zed, etc.) at https://your-server/mcp.
Note: MCP OAuth authentication is not implemented yet. Handle auth at the reverse proxy level instead (IP allowlist, VPN, etc.).
| Tool | Description |
| --------------- | -------------------------------------------------------------- |
| get_qr | Display the Lovense pairing QR code |
| get_toys | List connected toys and connection status |
| play_action | Single action: vibrate, rotate, thrust, etc. |
| stroke_action | Stroke + Thrusting for stroker toys (Solace, etc.) |
| play_preset | Built-in Lovense patterns (pulse, wave, fireworks, earthquake) |
| play_pattern | Smooth intensity timeline with custom waypoints |
| play_sequence | Multi-phase timed sequence (A then B then C, non-looping) |
| stop | Emergency stop — halts everything immediately |
Your AI should always call get_toys first to check connectivity and see which actions each toy actually supports. You normally don't need to specify it.
Sending a Rotate command to a toy that only vibrates ends in disappointment for everyone.
get_qrGenerates and displays the Lovense pairing QR code. Use this when get_toys returns no toys or lastSeenAt is null — the app isn't connected yet.
The user scans the QR code with the Lovense Remote app on their phone to establish the connection. After scanning, the server starts receiving heartbeats and toys become available.
No parameters. Returns the QR code as an image, plus a fallback URL if the image can't be displayed.
The QR code expires after 4 hours. Call
get_qragain to get a fresh one.
get_toysReturns the cached toy list from the last heartbeat. No API call to Lovense — just the server's in-memory state.
Output: { toys: [...], lastSeenAt: "ISO date or null" }
Each toy includes a features array listing its supported actions.
If lastSeenAt is null or more than 30 seconds old, the app is considered offline and any command will fail with a clear error message rather than silently doing nothing.
play_actionSingle action for a given duration.
| Parameter | Type | Description |
| ---------- | ------- | ---------------------------------------- |
| type | string | Action type (see table below) |
| strength | integer | Intensity (range depends on action) |
| duration | number | Seconds. 0 = indefinite, otherwise ≥ 1 |
| toyId | string? | Target a specific toy. Omit for all. |
Action types and ranges:
| Action | Range | Notes | | --------- | ----- | --------------------------------------- | | Vibrate | 0–20 | | | Rotate | 0–20 | | | Thrusting | 0–20 | | | Fingering | 0–20 | | | Suction | 0–20 | | | Oscillate | 0–20 | | | All | 0–20 | Applies to all functions simultaneously | | Pump | 0–3 | 3 levels only | | Depth | 0–3 | 3 levels only |
stroke_actionFor stroker toys (Solace, etc.) that support the Stroke action. Only use if get_toys shows "Stroke" in the toy's features — otherwise you're just wishing.
| Parameter | Type | Description |
| ------------------- | ------- | ---------------------------------------------- |
| strokeMin | integer | Start position (0–100, 0 = fully retracted) |
| strokeMax | integer | End position (0–100, must be ≥ strokeMin + 20) |
| thrustingStrength | integer | Speed 0–20 |
| duration | number | Seconds. 0 = indefinite, otherwise ≥ 1 |
| toyId | string? | Target a specific toy. Omit for all. |
Amplitude guide: very light = 0–20, light = 0–30, medium = 0–50, strong = 0–80, max = 0–100.
For variable-intensity stroking patterns over time, use play_pattern_v2 instead.
play_presetPlays a built-in Lovense pattern. Quick and easy when you don't want to think too hard.
| Parameter | Type | Description |
| ---------- | ------- | --------------------------------------------- |
| name | string | pulse / wave / fireworks / earthquake |
| duration | number | Seconds. 0 = indefinite, otherwise ≥ 1 |
| toyId | string? | Target a specific toy. Omit for all. |
play_patternThe most expressive tool. Defines a smooth intensity timeline — the Lovense app handles all timing internally. The server sends the points and gets out of the way.
| Parameter | Type | Description |
| --------- | ------- | -------------------------------------------------------------- |
| actions | array | Timeline of { ts, pos } waypoints, ordered by ascending ts |
| toyId | string? | Target a specific toy. Omit for all. |
ts: timestamp in milliseconds from start (max 7,200,000 = 2h)pos: intensity 0–100 (0 = off, 50 = medium, 100 = max)The app interpolates smoothly between consecutive points — they are waypoints, not discrete jumps. {ts:0, pos:0} → {ts:5000, pos:100} produces a gradual ramp over 5s automatically.
For sharp transitions, place two points ~100ms apart.
Always end with pos: 0 — the toy will otherwise hold the last position indefinitely. The API won't stop it on its own. You've been warned.
Examples:
// Ramp up over 10s, then stop
[
{ ts: 0, pos: 0 },
{ ts: 10000, pos: 100 },
{ ts: 10100, pos: 0 },
][
// Slow wave, 3 cycles of 4s
({ ts: 0, pos: 0 },
{ ts: 2000, pos: 100 },
{ ts: 4000, pos: 0 },
{ ts: 6000, pos: 100 },
{ ts: 8000, pos: 0 },
{ ts: 10000, pos: 100 },
{ ts: 12000, pos: 0 })
][
// 5s strong, 10s pause, 30s medium, stop
({ ts: 0, pos: 80 },
{ ts: 5000, pos: 0 },
{ ts: 15000, pos: 50 },
{ ts: 45000, pos: 0 })
];
play_sequenceExecutes a timed multi-phase sequence of steps. Returns immediately — scheduling runs server-side. Use this (not play_pattern) when:
Each step has a duration (seconds) and either "Stop" or an array of simultaneous actions.
| Parameter | Type | Description |
| --------- | ------- | --------------------------------------------- |
| steps | array | Ordered list of { duration, actions } steps |
| toyId | string? | Target a specific toy. Omit for all. |
Returns { sequenceId, totalDuration }. Calling stop cancels any running sequence automatically.
Examples:
// Strong 5s → max 10s → pause 30s → medium 30s
[
{ duration: 5, actions: [{ type: "Vibrate", strength: 16 }] },
{ duration: 10, actions: [{ type: "Vibrate", strength: 20 }] },
{ duration: 30, actions: "Stop" },
{ duration: 30, actions: [{ type: "Vibrate", strength: 10 }] },
]
// Vibrate + Rotate simultaneously at different strengths
[{ duration: 10, actions: [{ type: "Vibrate", strength: 15 }, { type: "Rotate", strength: 8 }] }]
// Vibrate phase then switch to Thrusting
[
{ duration: 20, actions: [{ type: "Vibrate", strength: 13 }] },
{ duration: 20, actions: [{ type: "Thrusting", strength: 10 }] },
]
// Medium-amplitude thrust (Stroke toy): Stroke must always be paired with Thrusting
[{ duration: 10, actions: [{ type: "Stroke", min: 0, max: 50 }, { type: "Thrusting", strength: 10 }] }]
stopStops everything immediately. Sends both a Function stop and a PatternV2 stop in parallel, because when you want it to stop, you want it to stop.
| Parameter | Type | Description |
| --------- | ------- | ------------------------------------ |
| toyId | string? | Target a specific toy. Omit for all. |
| Description | 0–20 | 0–3 | 0–100 | | ------------- | ---- | --- | ----- | | Very light | 3 | 1 | 15 | | Light | 6 | 1 | 30 | | Medium | 10 | 2 | 50 | | Fairly strong | 13 | 2 | 65 | | Strong | 16 | 3 | 80 | | Max | 20 | 3 | 100 |
| Variable | Required | Default | Description |
| ---------------- | -------- | ------------ | ------------------------------------------------------- |
| LOVENSE_TOKEN | ✓ | — | Developer token from the Lovense portal |
| LOVENSE_UID | ✓ | — | User identifier for your app |
| LOVENSE_UNAME | ✓ | — | Display name shown in Lovense Remote |
| LOVENSE_UTOKEN | ✓ | — | Arbitrary user token (any string you choose) |
| SETUP_TOKEN | ✓ | — | Protects the /setup page |
| MCP_PORT | | 3000 | Port the server listens on |
| NODE_ENV | | production | development enables pretty logs and debug level |
| LOG_LEVEL | | info | trace / debug / info / warn / error / fatal |
Tokens are never logged. Not even by accident.
| Endpoint | Description |
| ---------------------- | -------------------------------------- |
| GET /mcp | MCP transport (used by your AI client) |
| POST /callback | Lovense heartbeat receiver |
| GET /setup?token=xxx | QR code setup page |
| GET /health | Health check → { ok: true } |
bun run dev # watch mode, pretty logs, NODE_ENV=development
bun run start # production
bun run typecheck # type check only
Set LOG_LEVEL=debug to see full request/response bodies and AppState dumps. LOG_LEVEL=trace for internals.
Honestly tested with actual hardware:
| Feature | Status |
| ---------------------------------------------- | --------------------------------- |
| play_action → Vibrate | ✅ Works |
| play_pattern, play_sequence, play_preset | ✅ Works (vibration tested only) |
| get_toys, stop, get_qr | ✅ Works |
| play_action → Rotate, Pump, Thrusting, etc. | 🟡 Implemented per spec, untested |
| stroke_action | 🟡 Implemented per spec, untested |
The untested tools are implemented exactly according to the Lovense Server API docs and should work fine. I just don't own the entire Lovense catalog — I'm doing my best here, I assure you. PRs with real-world test reports are genuinely welcome.
MIT
Machine endpoints, protocol fit, contract coverage, invocation examples, and guardrails for agent-to-agent use.
Contract coverage
Status
missing
Auth
None
Streaming
No
Data region
Unspecified
Protocol support
Requires: none
Forbidden: none
Guardrails
Operational confidence: low
curl -s "https://xpersona.co/api/v1/agents/mcp-gradleless-lovense-mcp/snapshot"
curl -s "https://xpersona.co/api/v1/agents/mcp-gradleless-lovense-mcp/contract"
curl -s "https://xpersona.co/api/v1/agents/mcp-gradleless-lovense-mcp/trust"
Trust and runtime signals, benchmark suites, failure patterns, and practical risk constraints.
Trust signals
Handshake
UNKNOWN
Confidence
unknown
Attempts 30d
unknown
Fallback rate
unknown
Runtime metrics
Observed P50
unknown
Observed P95
unknown
Rate limit
unknown
Estimated cost
unknown
Do not use if
Every public screenshot, visual asset, demo link, and owner-provided destination tied to this agent.
Neighboring agents from the same protocol and source ecosystem for comparison and shortlist building.
Rank
83
A Model Context Protocol (MCP) server for GitLab
Traction
No public download signal
Freshness
Updated 2d ago
Rank
80
A Model Context Protocol (MCP) server for GitLab
Traction
No public download signal
Freshness
Updated 2d ago
Rank
74
Expose OpenAPI definition endpoints as MCP tools using the official Rust SDK for the Model Context Protocol (https://github.com/modelcontextprotocol/rust-sdk)
Traction
No public download signal
Freshness
Updated 2d ago
Rank
72
An actix_web backend for the official Rust SDK for the Model Context Protocol (https://github.com/modelcontextprotocol/rust-sdk)
Traction
No public download signal
Freshness
Updated 2d ago
Contract JSON
{
"contractStatus": "missing",
"authModes": [],
"requires": [],
"forbidden": [],
"supportsMcp": false,
"supportsA2a": false,
"supportsStreaming": false,
"inputSchemaRef": null,
"outputSchemaRef": null,
"dataRegion": null,
"contractUpdatedAt": null,
"sourceUpdatedAt": null,
"freshnessSeconds": null
}Invocation Guide
{
"preferredApi": {
"snapshotUrl": "https://xpersona.co/api/v1/agents/mcp-gradleless-lovense-mcp/snapshot",
"contractUrl": "https://xpersona.co/api/v1/agents/mcp-gradleless-lovense-mcp/contract",
"trustUrl": "https://xpersona.co/api/v1/agents/mcp-gradleless-lovense-mcp/trust"
},
"curlExamples": [
"curl -s \"https://xpersona.co/api/v1/agents/mcp-gradleless-lovense-mcp/snapshot\"",
"curl -s \"https://xpersona.co/api/v1/agents/mcp-gradleless-lovense-mcp/contract\"",
"curl -s \"https://xpersona.co/api/v1/agents/mcp-gradleless-lovense-mcp/trust\""
],
"jsonRequestTemplate": {
"query": "summarize this repo",
"constraints": {
"maxLatencyMs": 2000,
"protocolPreference": [
"MCP"
]
}
},
"jsonResponseTemplate": {
"ok": true,
"result": {
"summary": "...",
"confidence": 0.9
},
"meta": {
"source": "GITHUB_MCP",
"generatedAt": "2026-04-17T00:04:37.774Z"
}
},
"retryPolicy": {
"maxAttempts": 3,
"backoffMs": [
500,
1500,
3500
],
"retryableConditions": [
"HTTP_429",
"HTTP_503",
"NETWORK_TIMEOUT"
]
}
}Trust JSON
{
"status": "unavailable",
"handshakeStatus": "UNKNOWN",
"verificationFreshnessHours": null,
"reputationScore": null,
"p95LatencyMs": null,
"successRate30d": null,
"fallbackRate": null,
"attempts30d": null,
"trustUpdatedAt": null,
"trustConfidence": "unknown",
"sourceUpdatedAt": null,
"freshnessSeconds": null
}Capability Matrix
{
"rows": [
{
"key": "MCP",
"type": "protocol",
"support": "unknown",
"confidenceSource": "profile",
"notes": "Listed on profile"
}
],
"flattenedTokens": "protocol:MCP|unknown|profile"
}Facts JSON
[
{
"factKey": "docs_crawl",
"category": "integration",
"label": "Crawlable docs",
"value": "6 indexed pages on the official domain",
"href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
"sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
"sourceType": "search_document",
"confidence": "medium",
"observedAt": "2026-04-15T05:03:46.393Z",
"isPublic": true
},
{
"factKey": "vendor",
"category": "vendor",
"label": "Vendor",
"value": "Gradleless",
"href": "https://github.com/Gradleless/lovense-mcp",
"sourceUrl": "https://github.com/Gradleless/lovense-mcp",
"sourceType": "profile",
"confidence": "medium",
"observedAt": "2026-02-25T02:57:54.052Z",
"isPublic": true
},
{
"factKey": "protocols",
"category": "compatibility",
"label": "Protocol compatibility",
"value": "MCP",
"href": "https://xpersona.co/api/v1/agents/mcp-gradleless-lovense-mcp/contract",
"sourceUrl": "https://xpersona.co/api/v1/agents/mcp-gradleless-lovense-mcp/contract",
"sourceType": "contract",
"confidence": "medium",
"observedAt": "2026-02-25T02:57:54.052Z",
"isPublic": true
},
{
"factKey": "handshake_status",
"category": "security",
"label": "Handshake status",
"value": "UNKNOWN",
"href": "https://xpersona.co/api/v1/agents/mcp-gradleless-lovense-mcp/trust",
"sourceUrl": "https://xpersona.co/api/v1/agents/mcp-gradleless-lovense-mcp/trust",
"sourceType": "trust",
"confidence": "medium",
"observedAt": null,
"isPublic": true
}
]Change Events JSON
[
{
"eventType": "docs_update",
"title": "Docs refreshed: Sign in to GitHub · GitHub",
"description": "Fresh crawlable documentation was indexed for the official domain.",
"href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
"sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
"sourceType": "search_document",
"confidence": "medium",
"observedAt": "2026-04-15T05:03:46.393Z",
"isPublic": true
}
]Sponsored
Ads related to lovense-mcp and adjacent AI workflows.