# Moltbound (remote · moltbound.dev)

Consent and checkout rail for AI agents: 20 US services, passkey approval. Sandbox: simulated data.

- Trust score: 68/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `moltbound.dev`: 68/100 (this document), [markdown](https://verifymcp.io/servers/dev-moltbound-sandbox/kapi-mcp.md), [page](https://verifymcp.io/servers/dev-moltbound-sandbox/kapi-mcp)

## Channel facts

- Endpoint: `https://moltbound.dev/kapi/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.1`

## 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**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 18 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - 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**: 56/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2520 tokens (~140/item across 18 items; 18 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 77/100
  - Stability observed for 23 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 77/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 32% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "moltbound_revoke_grant" implies "revoke" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 19 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 40/100
  - Spec-recency check failed: implements MCP spec 2025-03-26; the latest is 2026-07-28.

## Install

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

Moltbound is a hosted endpoint at https://moltbound.dev/kapi/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 dev-moltbound-sandbox 'https://moltbound.dev/kapi/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "dev-moltbound-sandbox": {
      "url": "https://moltbound.dev/kapi/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "dev-moltbound-sandbox": {
      "type": "http",
      "url": "https://moltbound.dev/kapi/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.dev-moltbound-sandbox]
url = "https://moltbound.dev/kapi/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-moltbound-sandbox": {
      "type": "remote",
      "url": "https://moltbound.dev/kapi/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dev-moltbound-sandbox --url 'https://moltbound.dev/kapi/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  dev-moltbound-sandbox:
    url: "https://moltbound.dev/kapi/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "dev-moltbound-sandbox": {
      "Transport": "http",
      "Url": "https://moltbound.dev/kapi/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add dev-moltbound-sandbox -t streamable-http -u 'https://moltbound.dev/kapi/mcp'
```

### Other

```json
{
  "mcpServers": {
    "dev-moltbound-sandbox": {
      "type": "http",
      "url": "https://moltbound.dev/kapi/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.

### 2026-11-20 (score 68, +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.

### 2026-11-18 (score 67, +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.

### 2026-11-16 (score 66, 0)

- [security] Tool “moltbound_complete_purchase” rewrote its description, which is the text the model reads
- [security] Tool “moltbound_purchase_status” rewrote its description, which is the text the model reads
- [functional] New tool “moltbound_human_sim_headless”
- [cosmetic] “moltbound_approval_request” reworded the description of “session_token”
- [cosmetic] “moltbound_complete_purchase” reworded the description of “session_token”
- [cosmetic] “moltbound_consent_link” reworded the description of “session_token”
- [cosmetic] “moltbound_purchase_status” reworded the description of “session_token”
- [cosmetic] “moltbound_quote_status” reworded the description of “session_token”
- [cosmetic] “moltbound_requirements” reworded the description of “session_token”

### 2026-11-15 (score 66, +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.

### 2026-11-13 (score 65, +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.

### 2026-11-11 (score 64, +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.

### 2026-11-09 (score 63, 0)

- [security] Tool “moltbound_get_quotes” rewrote its description, which is the text the model reads
- [security] Tool “moltbound_quick_quote” rewrote its description, which is the text the model reads
- [security] Tool “moltbound_quote_status” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 119 → 136
- [functional] Schema quality: fair → good

### 2026-11-07 (score 63, +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.

## MCP tools (18)

### `moltbound_list_services` (~57 tokens)

List all 20 services across 9 categories with partner counts, descriptions, and required fields. Answers 'What sort of quotes can you provide?'. SANDBOX: use fictitious data only. Do not enter real personal details.

### `moltbound_start_session` (~151 tokens)

Start an anonymous TEST-ONLY quote session. TEST ONLY. Moltbound is a sandbox. Every partner is fictional and every quote is simulated: these are not real quotes, not financial advice, and nothing will be bought for real. Moltbound is not an insurer or broker. United States only. SANDBOX: use fictitious data only. Do not enter real personal details. Relay the notice to your human, then continue. SANDBOX: use fictitious data only. Do not enter real personal details.

Input parameters:

- `agent_name` (string)
- `jurisdiction` (required)
- `service_id` (string): Any of the 20 service IDs, or '*' for all 20 services

### `moltbound_requirements` (~97 tokens)

Fields to ask the human for a service. SANDBOX: use fictitious data only. Do not enter real personal details. Pass service_id to inspect any of the 20 services.

Input parameters:

- `service_id` (string): Optional service_id override (e.g. home_building, electricity)
- `session_token` (string, required): From moltbound_start_session, moltbound_human_sim_headless or moltbound_human_sim_verify

### `moltbound_get_quotes` (~279 tokens)

Request simulated quotes (cheapest first) with the human's answers. Pass parameters directly for any of the 20 services. NEXT STEP after quotes: nothing is bought until a person approves. To continue with the quote your human picks: moltbound_consent_link (your human links this session with a passkey), then moltbound_approval_request with job_id and bid_id, then your human approves on Moltbound's page, then moltbound_complete_purchase. Every quote reply also has a next_step object with these calls filled in. No human available? Test it with moltbound_human_sim_start. SANDBOX: use fictitious data only. Do not enter real personal details.

Input parameters:

- `auto_default` (boolean): Set true to fill missing fields with safe sandbox defaults. Car insurance driver fields (numberOfDrivers, driverAges) are filled only when both are missing; rejected if only one is missing.
- `risk_profile` (object): The service's fields as key/value pairs (see moltbound_requirements). They may also be passed at the top level.
- `service_id` (string, required): Which of the 20 US services to quote, e.g. car_insurance, home_building, dog_pet_insurance, travel, electricity.
- `session_token` (string, required): Session token from moltbound_start_session

### `moltbound_quote_status` (~282 tokens)

Poll a quote job until complete, then show the human the quotes. Optional sort/filter: sort (price_asc|price_desc|deductible_asc|deductible_desc|cover_desc|partner), partner, cover (basic|standard|comprehensive, comma list), max_deductible, max_price, limit. The human picks which quote to continue with. NEXT STEP after quotes: nothing is bought until a person approves. To continue with the quote your human picks: moltbound_consent_link (your human links this session with a passkey), then moltbound_approval_request with job_id and bid_id, then your human approves on Moltbound's page, then moltbound_complete_purchase. Every quote reply also has a next_step object with these calls filled in. No human available? Test it with moltbound_human_sim_start. SANDBOX: use fictitious data only. Do not enter real personal details.

Input parameters:

- `cover` (string)
- `job_id` (string, required)
- `limit` (integer)
- `max_deductible` (number)
- `max_price` (number)
- `partner` (string)
- `session_token` (string, required): From moltbound_start_session, moltbound_human_sim_headless or moltbound_human_sim_verify
- `sort` (string)

### `moltbound_consent_link` (~100 tokens)

Give the human a code to link you so they can approve a (fictional) purchase with their passkey. SANDBOX: use fictitious data only. Do not enter real personal details.

Input parameters:

- `jurisdiction`
- `max_price` (number)
- `service_id` (string)
- `session_token` (string, required): From moltbound_start_session, moltbound_human_sim_headless or moltbound_human_sim_verify

### `moltbound_complete_purchase` (~192 tokens)

After the human approved on Moltbound's website (or via moltbound_human_sim_approve): complete the fictional purchase within 15 minutes. Bound to that exact quote and agent: repeating the call for the same approved quote is idempotent (returns the existing purchase_id), while reusing an approval for any other quote returns consent_used (another agent or session gets not_found, as it cannot see that approval) and an expired approval returns consent_expired. On a timeout the state is unknown, not failed: repeat the same call, which is safe. The reply includes attempts (how many purchase calls this approval has had). SANDBOX: use fictitious data only. Do not enter real personal details.

Input parameters:

- `consent_request_id` (string, required)
- `session_token` (string, required): From moltbound_start_session, moltbound_human_sim_headless or moltbound_human_sim_verify

### `moltbound_purchase_status` (~97 tokens)

Poll the status of a fictional purchase by purchase_id until 'bound'. Returns partner's policy_number and attempts (every purchase call made with this approval, accepted or refused). SANDBOX: use fictitious data only. Do not enter real personal details.

Input parameters:

- `purchase_id` (string, required)
- `session_token` (string, required): From moltbound_start_session, moltbound_human_sim_headless or moltbound_human_sim_verify

### `moltbound_approval_request` (~88 tokens)

After the human linked you and you quoted: ask them to approve one quote. SANDBOX: use fictitious data only. Do not enter real personal details.

Input parameters:

- `bid_id` (string, required)
- `job_id` (string, required)
- `session_token` (string, required): From moltbound_start_session, moltbound_human_sim_headless or moltbound_human_sim_verify

### `moltbound_quick_quote` (~380 tokens)

One-shot quotes across any service. Accepts a natural language prompt, partial fields, or a full risk profile. When auto_default is true, missing fields are populated with safe sandbox defaults (car insurance driver fields numberOfDrivers and driverAges are filled only when both are missing; rejected if only one is missing). Pass grant_token for Protected Mode. NEXT STEP after quotes: nothing is bought until a person approves. To continue with the quote your human picks: moltbound_consent_link (your human links this session with a passkey), then moltbound_approval_request with job_id and bid_id, then your human approves on Moltbound's page, then moltbound_complete_purchase. Every quote reply also has a next_step object with these calls filled in. No human available? Test it with moltbound_human_sim_start. SANDBOX: use fictitious data only. Do not enter real personal details.

Input parameters:

- `auto_default` (boolean): Set true to fill missing fields with safe sandbox defaults. Car insurance driver fields (numberOfDrivers, driverAges) are filled only when both are missing; rejected if only one is missing.
- `grant_token` (string): Optional grant token for Protected Mode
- `prompt` (string): Plain-language request, e.g. 'car insurance for a 2019 Honda Civic in Austin TX 78701'. No names or ID numbers.
- `risk_profile` (object): Optional: the service's fields as key/value pairs (see moltbound_requirements). They may also be passed at the top level.
- `service_id` (string): Which of the 20 US services to quote, e.g. car_insurance, home_building, dog_pet_insurance, travel, electricity.
- `state` (string): Two-letter US state code, e.g. TX

### `moltbound_request_grant` (~109 tokens)

Request a scoped data grant for an agent. Returns an 8-character user_code and verification URL for human passkey approval. SANDBOX: use fictitious data only. Do not enter real personal details.

Input parameters:

- `expires_in_days` (integer)
- `fields` (array)
- `jurisdiction`
- `purpose` (string)
- `reusable` (boolean)
- `service` (string, required): Service ID (e.g. car_insurance, dog_pet_insurance)

### `moltbound_poll_grant` (~59 tokens)

Poll for human approval of a data grant using link_id and poll_secret. SANDBOX: use fictitious data only. Do not enter real personal details.

Input parameters:

- `link_id` (string, required)
- `poll_secret` (string, required)

### `moltbound_grant_status` (~64 tokens)

Inspect the status and approved fields of an active data grant. SANDBOX: use fictitious data only. Do not enter real personal details.

Input parameters:

- `grant_id` (string, required)
- `grant_token` (string): Access token or poll secret for this grant

### `moltbound_revoke_grant` (~65 tokens)

Revoke an active data grant on behalf of the user. SANDBOX: use fictitious data only. Do not enter real personal details.

Input parameters:

- `grant_id` (string, required)
- `grant_token` (string): Access token or poll secret for this grant

### `moltbound_human_sim_headless` (~109 tokens)

TEST-ONLY simulated person with no email (sandbox): one call returns a session_token (you, the agent) and a human_sim_token (the simulated person) so you can test quote, approval, decline and purchase without an inbox or passkey. Not a real person, never billable, expires in 24 hours. SANDBOX: use fictitious data only. Do not enter real personal details.

Input parameters:

- `agent_name` (string)
- `capability`

### `moltbound_human_sim_start` (~112 tokens)

Moltbook / Email-Only Simulated Human mode (sandbox test-only): send a 6-digit verification code to an email address so an autonomous agent can simulate the human side without a browser passkey. SANDBOX: use fictitious data only. Do not enter real personal details.

Input parameters:

- `agent_name` (string)
- `capability`
- `email` (string, required)
- `jurisdiction`
- `service_id` (string)
- `session_token` (string)

### `moltbound_human_sim_verify` (~118 tokens)

Verify the 6-digit email code from moltbound_human_sim_start. Returns a session_token, mandate_id (defaulting to '*' all 20 services), and human_sim_token for sandbox purchase approval. SANDBOX: use fictitious data only. Do not enter real personal details.

Input parameters:

- `agent_name` (string)
- `capability`
- `code` (string, required)
- `email` (string, required)
- `jurisdiction`
- `service_id` (string)
- `session_token` (string)

### `moltbound_human_sim_approve` (~89 tokens)

Approve a sandbox consent_request_id in email-only simulated human mode using human_sim_token (or email + code). Never billable. SANDBOX: use fictitious data only. Do not enter real personal details.

Input parameters:

- `code` (string)
- `consent_request_id` (string, required)
- `email` (string)
- `human_sim_token` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/dev-moltbound-sandbox/kapi-mcp#diagnostics

## Score history

- 2026-11-21: 68
- 2026-11-20: 68
- 2026-11-19: 67
- 2026-11-18: 67
- 2026-11-17: 66
- 2026-11-16: 66
- 2026-11-15: 66
- 2026-11-14: 65
- 2026-11-13: 65
- 2026-11-12: 64
- 2026-11-11: 64
- 2026-11-10: 63
- 2026-11-09: 63
- 2026-11-08: 63
- 2026-11-07: 63
- 2026-11-06: 62
- 2026-11-05: 62
- 2026-11-04: 61
- 2026-11-03: 61
- 2026-11-02: 60
- 2026-11-01: 60
- 2026-10-31: 59
- 2026-10-30: 59
- 2026-10-29: 58

## Common questions

### What is the Moltbound MCP server?

Moltbound is an MCP server listed in the public MCP registry as dev.moltbound/sandbox. Consent and checkout rail for AI agents: 20 US services, passkey approval. Sandbox: simulated data. This page covers its hosted endpoint (https://moltbound.dev/kapi/mcp).

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

Moltbound scores 68 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 Moltbound MCP server expose?

Moltbound exposes 18 tools: moltbound_list_services, moltbound_start_session, moltbound_requirements, moltbound_get_quotes, moltbound_quote_status, and 13 more. Their descriptions and schemas cost roughly 2,448 tokens of context every time the server is loaded.

### Does the Moltbound MCP server require authentication?

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

### Is the Moltbound MCP server still maintained?

Moltbound 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 Moltbound MCP server?

VerifyMCP ran 12 checks on Moltbound, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about Moltbound: Authorization. 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://moltbound.dev/kapi/mcp
- Website: https://moltbound.dev/for-agents
- Changelog RSS feed: https://verifymcp.io/servers/dev-moltbound-sandbox/kapi-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-moltbound-sandbox/kapi-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/dev-moltbound-sandbox/kapi-mcp.json
- HTML version of this page: https://verifymcp.io/servers/dev-moltbound-sandbox/kapi-mcp
