Keplr Wallet MCP Server
@keplr-wallet/keplr-wallet-mcp
npm
v0.0.8
Source verified
Published by chainapsis — publish provenance cryptographically ties this package to that repository. That is proof of origin, not an official vendor package.
Keplr MCP Server — AI agents can interact with Cosmos chains via Model Context Protocol
The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.
1. Threat score — 100 − 0 = 100. What the published surface and source actually contain:
The deterministic scan raised no scored threat in the surface it inspected — the threat score stayed at 100. Capability observations and advisory notes are recorded but never lower it.
2. Client adoption risk — 100 − 6 = 94. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:
| Points | Adoption-risk factor |
|---|---|
| −6 | capability blast radius (high) — client exposure if the model is manipulated |
Capability observations and info notes are shown under Findings but never scored.
Open any row's finding below for the file, line and evidence behind a deduction.
Findings 7
high Shell/command execution in server code (dist/auth/providers/biometric.js)MTC-SRC-002
In the server's implementation (`dist/auth/providers/biometric.js:7`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { execFile } from "node:child_process"; import { existsSync } from "node:fs"; import { promisify } from "node:util"; imp
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/auth/providers/biometric.js
high Shell/command execution in server code (dist/vault-key.js)MTC-SRC-002
In the server's implementation (`dist/vault-key.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { execFile } from "node:child_process"; import { existsSync } from "node:fs"; import { promisify } from "node:util"; imp
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/vault-key.js
high Shell/command execution in server code (dist/vault.js)MTC-SRC-002
In the server's implementation (`dist/vault.js:1`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { execFile } from "node:child_process"; import { createCipheriv, createDecipheriv, randomBytes } from "node:crypto"; imp
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/vault.js
high Shell/command execution in server code (dist/webauthn/cli-handler.js)MTC-SRC-002
In the server's implementation (`dist/webauthn/cli-handler.js:12`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: { execFile } from "node:child_process"; import { existsSync } from "node:fs"; import { promisify } from "node:util"; imp
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/webauthn/cli-handler.js
medium Dynamic module load from a non-literal (dist/adapter-loader.js)MTC-SRC-005
In the server's implementation (`dist/adapter-loader.js:36`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const mod = await import(name); const factory = mod.default; if (typeof factory !== "funct
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/adapter-loader.js
medium Dynamic module load from a non-literal (dist/config/loader.js)MTC-SRC-005
In the server's implementation (`dist/config/loader.js:31`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const mod = await import(filepath); const config = mod.default ?? mod; return mergeEnvVars(config)
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/config/loader.js
medium Dynamic module load from a non-literal (dist/index.js)MTC-SRC-005
In the server's implementation (`dist/index.js:44`): Loading a module chosen at runtime (from a variable) can pull in and run attacker-influenced code paths. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.
Evidence: const mod = await import(entry); const factory = mod.default ?? mod; const resolved = type
Fix: Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.
Location: server dist/index.js
Tools 68
Each tool and what it can reach — statically extracted from the published source.
cosmwasm-executenetwork egressauth-available-methodsno sensitive capabilityauth-disableno sensitive capabilityauth-enableno sensitive capabilityauth-provider-disableno sensitive capabilityauth-setupno sensitive capabilityauth-statusno sensitive capabilityauth-verify-setupno sensitive capabilitycancel-pending-actionno sensitive capabilitycancel-unbondingno sensitive capability
Show 58 more tools ↓
check-vault-healthno sensitive capabilityclaim-all-rewardsno sensitive capabilityclaim-rewardsno sensitive capabilityconfirm-actionno sensitive capabilitycosmos-sign-arbitraryno sensitive capabilitycosmos-verify-signatureno sensitive capabilitycosmwasm-contract-infono sensitive capabilitycosmwasm-instantiateno sensitive capabilitycosmwasm-list-contractsno sensitive capabilitycosmwasm-queryno sensitive capabilitycreate-accountno sensitive capabilitydelegateno sensitive capabilitydelete-accountno sensitive capabilitydescribe-toolsno sensitive capabilityexport-mnemonicno sensitive capabilityget-account-addressesno sensitive capabilityget-balancesno sensitive capabilityget-cosmos-addressno sensitive capabilityget-portfoliono sensitive capabilityget-proposalno sensitive capabilityget-staking-infono sensitive capabilityget-transaction-statusno sensitive capabilityget-unbondingno sensitive capabilityibc-transferno sensitive capabilityimport-accountno sensitive capabilitykeplr_api_configure_keyno sensitive capabilitykeplr_api_get_credit_historyno sensitive capabilitykeplr_api_get_payment_linkno sensitive capabilitykeplr_api_get_usage_historyno sensitive capabilitykeplr_api_get_usage_summaryno sensitive capabilitykeplr_api_list_chainsno sensitive capabilitykeplr_api_validate_keyno sensitive capabilitylist-accountsno sensitive capabilitylist-cosmos-chainsno sensitive capabilitylist-fee-tokensno sensitive capabilitylist-ibc-channelsno sensitive capabilitylist-installed-adaptersno sensitive capabilitylist-pending-actionsno sensitive capabilitylist-proposalsno sensitive capabilitylist-transaction-historyno sensitive capabilitylist-validatorsno sensitive capabilitymulti-action-addno sensitive capabilitymulti-action-cancelno sensitive capabilitymulti-action-createno sensitive capabilitymulti-action-executeno sensitive capabilitymulti-action-listno sensitive capabilitymulti-action-previewno sensitive capabilitymulti-action-removeno sensitive capabilityonboarding-statusno sensitive capabilityosmosis-quoteno sensitive capabilityosmosis-swapno sensitive capabilityredelegateno sensitive capabilityrename-accountno sensitive capabilitysearch-toolsno sensitive capabilitysend-tokensno sensitive capabilityswitch-accountno sensitive capabilityundelegateno sensitive capabilityvote-governanceno sensitive capability
What this scan could not see
- Tools were statically extracted from the published source (68 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Versions 1
Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.
| Version | Score | Findings | Engine | Scanned |
|---|---|---|---|---|
v0.0.8 latest |
A 94/100 | 7 | 1.13.0 | 2026-09-07 |
Embed this score
Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.
Verify this score yourself
The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.
npx mcptrustchecker scan @keplr-wallet/keplr-wallet-mcp --onlineMore in API Development
Adapters for the FrontMCP framework
Transcend MCP Server — Admin tools.
Transcend MCP Server — Assessments tools.
MCP Server for Bling
MCP Server for Blogger API
Official MCP server for Brilliant Directories — manage members, posts, leads, reviews, and more.