Atlas / MCP servers / toolprint / Hypertool

HypertoolBLOCK

Name: Hypertool
Author: toolprint

mcp/toolprint/hypertool

MCP server by toolprint · agents · claude code · hypertool · Audited 2026-10-07

⚑ Report / re-scan Source ↗

Dynamically expose tools from proxied servers based on an Agent Persona

Verdict

BLOCK

Grade

Trust score

69 /100

Exposed tools

80 60r · 19w · 1d

Transport

stdio · streamable-http

License

NOASSERTION

Stars

155

Overview

From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.

Give your AI the best tools from all your MCPs 🎯

[](https://npmjs.com/package/@toolprint/hypertool-mcp) [](https://npmjs.com/package/@toolprint/hypertool-mcp) [](https://discord.gg/MbvndnJ45W) [](https://www.typescriptlang.org/) [](https://modelcontextprotocol.io) [](LICENSE)

⚡ Features

🔓 Break Free from Tool Limits

Connect unlimited MCP servers. Use 10, 50, or 500+ tools total - your AI only sees what it needs.

🎯 Task-Specific Toolsets

Build "git-essentials" with 5 tools instead of drowning in 47 Git commands. Switch contexts instantly.

🧠 Smart Tool Descriptions

Enhance tools with examples and context. Watch your AI pick the right tool 89% more often.

🚀 Quick Start

Step 1: Copy Your Existing Config

# In your project directory
cp .mcp.json .mcp.hypertool.json

Step 2: Point Your AI to HyperTool

Replace your .mcp.json with:

{
"mcpServers": {
"hypertool": {
"command": "npx",
"args": ["-y", "@toolprint/hypertool-mcp", "mcp", "run", "--mcp-config", ".mcp.hypertool.json"]

Read from source at commit a5df37f12690OBSERVED · 2026-10-07

Connect

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.

claude-code

claude mcp add hypertool-mcp -- npx -y @toolprint/[email protected]

claude-desktop

{
  "mcpServers": {
    "hypertool-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@toolprint/[email protected]"
      ]
    }
  }
}

Exposed tools (80)

60 read · 19 write · 1 destructive. Blast radius: 1 tool can delete or overwrite — an agent that can be talked into calling a tool can be talked into calling this one.

Tool	Risk	Description
`DevTools`	read	Development tools
`add-tool-annotation`	write	Add contextual annotations to a tool in the current toolset to guide LLM usage. Annotations provide user-specific guidance, best practices, and usage notes that will be displayed with the tool
`build-toolset`	read	Build a toolset
`cached_tool`	read	A cached tool
`commit`	write	Git commit tool
`complete-persona`	read	A complete persona configuration with all optional fields
`complex-integration-test`	read	Complex integration test persona
`config-without-tools`	read	A config that lacks tools array
`coverage.check`	read	Check code coverage
`create_issue`	write	Creates a new issue in Linear
`custom-name`	read	Custom description
`database.query`	write	Execute database query
`debugger.attach`	read	Attach debugger to process
`default-without-toolsets`	read	Configuration with default toolset but no toolsets array
`delete-toolset`	destructive	Delete a saved toolset configuration
`dev-tools`	read	Short
`docker.build`	read	Build docker image
`docker.compose.up`	write	Start docker-compose services
`docker.ps`	read	List running containers
`docker.run`	write	Run docker container
`duplicate-tools`	read	Configuration with duplicate tool IDs
`duplicate-toolsets`	read	Configuration with duplicate toolset names
`dxtEnabled`	write	Enable DXT extension system and management commands
`enableConfigToolsMenu`	read	Enables a dynamic configuration tools menu instead of showing all tools together
`enter-configuration-mode`	read	Enter configuration mode to manage toolsets
`equip-toolset`	read	Equip a saved toolset configuration to filter available tools
`exit-configuration-mode`	read	Leave configuration mode and return to normal operational mode. This will hide configuration tools and restore access to your equipped toolset
`extended-test`	read	Extended test persona
`filesystem.read`	read	Read file contents
`filesystem.write`	write	Write file contents
`get-active-persona`	read	Get information about the currently active persona. Returns the active persona
`get-active-toolset`	read	Get detailed information about the currently equipped toolset including availability status
`git.add`	write	Stage files for commit
`git.commit`	write	Commit staged changes
`git.push`	write	Push commits to remote
`git.status`	read	Get git repository status
`git_status`	read	Show the working tree status
`hello`	read	Returns a friendly greeting
`integration-test`	read	Integration test persona
`invalid-default`	read	Configuration with invalid default toolset
`jest.run`	write	Run Jest tests
`kubernetes.deploy`	write	Deploy to Kubernetes
`list-available-tools`	read	Discover all tools available from connected MCP servers
`list-personas`	read	List available personas with their validation status and metadata. Returns structured data showing all discovered personas with essential information for selection and activation.
`list-saved-toolsets`	read	List all saved toolset configurations with detailed information including server configurations and tool counts
`logs.search`	read	Search application logs
`logs.tail`	read	Tail application logs
`long-desc`	read	x
`max-desc`	read	x
`mcpLoggerEnabled`	read	Use experimental mcp-logger instead of default Pino logging
`metrics.query`	read	Query system metrics
`min-desc`	read	x
`minimal-persona`	read	A minimal persona configuration for testing purposes
`monitoring.check`	read	Check monitoring status
`new_tool`	read	A new tool
`no-toolsets`	read	A persona without any toolsets defined
`npm.build`	read	Build npm project
`npm.install`	write	Install npm dependencies
`npm.test`	write	Run npm tests
`partial-metadata`	read	Persona with partial metadata
`profiler.start`	write	Start performance profiling
`ps`	read	Docker ps tool
`read`	read	Read file from filesystem
`required-test`	read	Test with all required fields
`save-test`	write	Configuration for save test
`setupWizardEnabled`	write	Enable interactive setup wizard on first run (default: disabled)
`short-desc`	read	Too short
`simple-persona`	read	Simple test persona
`status`	read	Git status tool
`terraform.apply`	write	Apply Terraform configuration
`test`	read	Test configuration
`test-config`	read	Test configuration
`test-persona`	read	A test persona for archive tests
`test-toolset`	read	Test toolset
`test_tool`	read	A test tool
`unequip-toolset`	read	Unequip the currently equipped toolset and show all available tools
`unknown-fields`	read	Configuration with unknown fields
`valid-persona`	read	A valid persona configuration
`validate-persona`	read	Validate a specific persona
`wrong-name`	read	A persona with wrong name

Trust audit

BLOCKgrade D · trust 69/100 Do not install this without reading the findings. The audit found something that could harm you or your machine.

Layer	What it checks	Result
L0	Provenance & inventory	PASS
L1	Static analysis of the code	FAIL
L2	Instruction surface (what it tells the agent)	PASS
L3	Class-specific surface	WARN
L4	Behavioural (sandbox)	SKIPPED

What the source does

Filesystem: declared (10 observation(s))
Network: declared (11 observation(s))
Shell: declared (4 observation(s))
Dependencies: not all pinned
Secrets in source: found

Findings (23)

HIGHNetwork egress · net.tls_off · CWE-200, CWE-319

src/index.ts:157

flags: "--insecure",

Why it matters. certificate verification is disabled

Fix. leave verification on

MEDIUMHard-coded secrets · secret.private_key · CWE-798, CWE-321

.github/RULESET_SETUP.md:102

- `-----BEGIN OPENSSH PRIVATE KEY-----`

MEDIUMHard-coded secrets · secret.private_key · CWE-798, CWE-321

.github/RULESET_SETUP.md:172

- Ensure the deploy key is properly formatted (starts with `-----BEGIN OPENSSH PRIVATE KEY-----`)

MEDIUMHard-coded secrets · secret.slack · CWE-798, CWE-321

examples/mcp/mcp.everything-with-secrets.json:232

"SLACK_BOT_TOKEN": "xoxb-YOUR-SLACK-BOT-TOKEN-HERE",

MEDIUMFilesystem / path · mcp.destructive_tools · CWE-22, CWE-59

delete-toolset

Why it matters. 1 tool(s) can delete or overwrite

Fix. prefer a read-only mode or scoped tokens; the page states the blast radius

LOWInventory / provenance · inv.binary · CWE-1104

docs/design/persona-content-pack.md

persona-content-pack.md

Why it matters. a compiled or binary member cannot be reviewed from source

Fix. ship source, or explain the binary in the README

LOWInventory / provenance · inv.binary · CWE-1104

docs/tasks/persona-content-pack-tasks.md

persona-content-pack-tasks.md

Why it matters. a compiled or binary member cannot be reviewed from source

Fix. ship source, or explain the binary in the README