SdkSAFE
Integrate SettleMint into your application with ease.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
SettleMint SDK
✨ https://settlemint.com ✨
Integrate SettleMint into your application with ease.
Documentation • Issues
About
The SettleMint SDK provides a comprehensive set of tools and libraries for integrating blockchain functionality into your applications. It enables seamless interaction with the SettleMint platform's features and services.
Packages
c6bf5b6ecb5cOBSERVED · 2026-10-12Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add test-app --env SETTLEMINT_ACCESS_TOKEN=${SETTLEMINT_ACCESS_TOKEN} --env SETTLEMINT_ACCESS_TOKEN_E2E_TESTS=${SETTLEMINT_ACCESS_TOKEN_E2E_TESTS} --env SETTLEMINT_BLOCKCHAIN_ACCESS_TOKEN=${SETTLEMINT_BLOCKCHAIN_ACCESS_TOKEN} --env SETTLEMINT_HASURA_ADMIN_SECRET=${SETTLEMINT_HASURA_ADMIN_SECRET} -- npx -y [email protected]{
"mcpServers": {
"test-app": {
"command": "npx",
"args": [
"-y",
"[email protected]"
],
"env": {
"SETTLEMINT_ACCESS_TOKEN": "${SETTLEMINT_ACCESS_TOKEN}",
"SETTLEMINT_ACCESS_TOKEN_E2E_TESTS": "${SETTLEMINT_ACCESS_TOKEN_E2E_TESTS}",
"SETTLEMINT_BLOCKCHAIN_ACCESS_TOKEN": "${SETTLEMINT_BLOCKCHAIN_ACCESS_TOKEN}",
"SETTLEMINT_HASURA_ADMIN_SECRET": "${SETTLEMINT_HASURA_ADMIN_SECRET}"
}
}
}
}Exposed tools (56)
37 read · 19 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
Error | read | Error getting prompt |
hasura-mutation | read | |
hasura-mutations | read | |
hasura-queries | read | |
hasura-query | read | |
platform-application-list | read | |
platform-application-read | read | |
platform-blockchain-network-create | write | |
platform-blockchain-network-list | read | |
platform-blockchain-network-read | read | |
platform-blockchain-network-restart | write | |
platform-blockchain-node-create | write | |
platform-blockchain-node-list | read | |
platform-blockchain-node-read | read | |
platform-blockchain-node-restart | write | |
platform-custom-deployment-create | write | |
platform-custom-deployment-edit | write | |
platform-custom-deployment-list | read | |
platform-custom-deployment-read | read | |
platform-custom-deployment-restart | write | |
platform-insights-create | write | |
platform-insights-list | read | |
platform-insights-read | read | |
platform-insights-restart | write | |
platform-integration-tool-create | write | |
platform-integration-tool-list | read | |
platform-integration-tool-read | read | |
platform-integration-tool-restart | write | |
platform-load-balancer-create | write | |
platform-load-balancer-list | read | |
platform-load-balancer-read | read | |
platform-load-balancer-restart | write | |
platform-middleware-create | write | |
platform-middleware-list | read | |
platform-middleware-read | read | |
platform-middleware-restart | write | |
platform-private-key-create | write | |
platform-private-key-list | read | |
platform-private-key-read | read | |
platform-private-key-restart | write | |
platform-storage-create | write | |
platform-storage-list | read | |
platform-storage-read | read | |
platform-storage-restart | write | |
platform-workspace-list | read | |
platform-workspace-read | read | |
portal-mutation | read | |
portal-mutations | read | |
portal-queries | read | |
portal-query | read | |
prompts-get | read | |
prompts-list | read | |
resources-get | read | |
resources-list | read | |
thegraph-queries | read | |
thegraph-query | read |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (4 observation(s))
- Network
- declared (5 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (25)
* console.log(args.pat); // Personal Access Token
.bun-version
.node-version
logger.info("test message with token: sm_pat_1234567890", { token: "sm_pat_1234567890" });import { createNodePackage, withPerformanceMonitoring } from "../../shared/tsdown-factory.ts";import pkg from "../../package.json";
import { isRunning } from "../../utils/cluster-service";import pkg from "../../package.json";
import pkg from "../../package.json";
tsdown
@types/bun
gql.tada, graphql-request, zod
zod, yocto-spinner
gql.tada, viem, zod
sdk/portal/src/examples/schemas/portal-schema.graphql
<a href="#pause-evm">evm|lb</a> [options] <unique-name> Pause a load balancer in the SettleMint platform. Provide the load balancer unique name or use 'default' to pau
unique name or use 'default' to pause the default load balancer from your .env
<a href="#restart-load-balancer">load-balancer|lb</a> [options] <unique-name> Restart a load balancer in the SettleMint platform. Provide the load balancer unique name or use 'defaul
unique name or use 'default' to restart the default load balancer from your .env
<a href="#resume-load-balancer">load-balancer|lb</a> [options] <unique-name> Resume a load balancer in the SettleMint platform. Provide the load balancer unique name or use 'default&
Defined in: [sdk/utils/src/terminal/execute-command.ts:60](https://github.com/settlemint/sdk/blob/v2.6.12/sdk/utils/src/terminal/execute-command.ts#L60)
Defined in: [sdk/utils/src/terminal/execute-command.ts:16](https://github.com/settlemint/sdk/blob/v2.6.12/sdk/utils/src/terminal/execute-command.ts#L16)
Defined in: [sdk/utils/src/terminal/execute-command.ts:23](https://github.com/settlemint/sdk/blob/v2.6.12/sdk/utils/src/terminal/execute-command.ts#L23)
Defined in: [sdk/utils/src/terminal/execute-command.ts:25](https://github.com/settlemint/sdk/blob/v2.6.12/sdk/utils/src/terminal/execute-command.ts#L25)
Defined in: [sdk/utils/src/terminal/execute-command.ts:26](https://github.com/settlemint/sdk/blob/v2.6.12/sdk/utils/src/terminal/execute-command.ts#L26)
Gates applied: no_behavioural_pass.
c6bf5b6ecb5cfull audit observations/trust-audit/mcp-server/settlemint__sdk.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-12 | c6bf5b6ecb5c | SAFE | B | 89 | first audit |
Questions
What is the @settlemint/sdk-mcp MCP server?
Integrate SettleMint into your application with ease.
What tools does @settlemint/sdk-mcp expose?
56 in total: 37 read-only, 19 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is @settlemint/sdk-mcp safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does @settlemint/sdk-mcp need?
It reads SETTLEMINT_ACCESS_TOKEN, SETTLEMINT_ACCESS_TOKEN_E2E_TESTS, SETTLEMINT_BLOCKCHAIN_ACCESS_TOKEN, SETTLEMINT_HASURA_ADMIN_SECRET, SETTLEMINT_MINIO_ACCESS_KEY and SETTLEMINT_MINIO_SECRET_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does @settlemint/sdk-mcp run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as test-app at 1.0.0.
How current is this page?
The grade is for one exact copy of the source (c6bf5b6ecb5c), read on 2026-10-12. The repository is watched and re-audited when it changes.