Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@registry-tools search for MCP servers related to finance"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Search and resolve MCP server packages on the mpak registry. This server lets agents discover available MCP servers, inspect their tools, and check credential requirements before installation.
This is one of the core MCP servers that powers NimbleBrain's agent runtime, giving agents self-service access to the registry. It's open source so you can see how it works, fork it to connect to your own registry, or use it as a reference for building discovery-layer MCP servers.
mpak install @nimblebraininc/registry-toolsclaude mcp add registry-tools -- mpak run @nimblebraininc/registry-tools{
"mcpServers": {
"registry-tools": {
"command": "mpak",
"args": ["run", "@nimblebraininc/registry-tools"]
}
}
}Related MCP server: agentalmanac-mcp
Search the mpak registry for available MCP servers.
Parameter | Type | Required | Description |
|
| Yes | Search term (e.g., "weather", "pdf", "finance") |
Returns matching packages with name, description, tools, download count, and verification status.
Get full metadata for a specific package, including credential requirements and version history.
Parameter | Type | Required | Description |
|
| Yes | Package identifier (e.g., "@nimblebraininc/finnhub") |
|
| No | Specific version (omit for latest) |
Returns detailed package info including tools, required credentials, license, and homepage.
Env Var | Required | Description |
| No | mpak registry URL (default: |
Want to adapt this for your own infrastructure?
Point REGISTRY_URL at your own registry endpoint
Add a registry_browse tool that lists categories or popular servers
Add tools that combine search with automatic installation via your orchestrator
Fork and modify src/mcp_registry_tools/server.py
git clone https://github.com/NimbleBrainInc/mcp-registry-tools.git
cd mcp-registry-tools
# Install dependencies
uv sync --group dev
# Run all checks (format, lint, typecheck, tests)
make check
# Run the server locally (stdio)
uv run python -m mcp_registry_tools.server
# Run the server locally (HTTP)
make run-httpMIT
Get full metadata for a specific package from the mpak registry.
Includes credential requirements and available tools.
| Name | Required | Description | Default |
|---|---|---|---|
| package | Yes | Package identifier (e.g., '@nimblebraininc/finnhub'). | |
| version | No | Specific version. Omit for latest. |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It adds useful context that the metadata includes credential requirements and available tools, but does not disclose error handling, pagination, or any read-only guarantees. For a simple read tool, this is adequate but not rich.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the core purpose, and adds one notable detail about included metadata. There is no fluff or redundant information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the output schema exists, the description doesn't need to explain return structure. It covers the essential purpose and highlights credential requirements/tools. It could mention what happens for unknown packages, but this is a minor gap for a simple lookup tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, with clear descriptions for both 'package' and 'version'. The description itself adds no additional parameter semantics beyond what the schema already provides, so baseline 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function with a specific verb and resource: 'Get full metadata for a specific package from the mpak registry.' It distinguishes itself from the sibling registry_search by focusing on a specific package rather than searching.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage when you have a known package identifier and need full metadata, but it does not explicitly mention when to use this tool versus registry_search or provide exclusions/alternatives. Some context is present, but no direct guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search the mpak registry for available MCP servers.
Returns name, description, tools, version, and verification status.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search term (e.g., 'weather', 'pdf', 'finance'). |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It discloses the read-only search behavior and the specific fields returned (name, description, tools, version, verification status). It lacks detail on edge cases like pagination or result limits, but is adequate for a simple search tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the action, and contains no redundant information. It is concise and well-structured.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool is simple (one required parameter) and has an output schema, so the description is mostly complete. It covers the purpose and return fields, but does not guide users on when to prefer this over the sibling registry_resolve, leaving a minor gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already provides 100% coverage for the single 'query' parameter with an example. The description adds no parameter-level detail beyond what the schema states, so the baseline of 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool searches the mpak registry for MCP servers, using a specific verb and resource. It also enumerates the returned fields, making the purpose unambiguous and distinct from the sibling tool registry_resolve.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description clearly indicates when to use this tool (when searching the registry). However, it does not explicitly mention alternatives or exclusion criteria, such as when to use registry_resolve instead.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.1registry_resolveregistry_searchScored across 2 tools
The two tools have distinct purposes: registry_search is for discovering packages via query, while registry_resolve fetches detailed metadata for a known package. They could be confused if users expect search to return full details, but descriptions clarify the difference.
Both tool names follow a consistent pattern: 'registry_' prefix plus a verb (search, resolve). This makes the naming predictable and easy to navigate.
With only 2 tools, the set feels thin for a registry service, which typically includes list, publish, or management operations. However, for a read-only lookup/query server, this minimal set may be intentionally scoped.
The tools cover search and detailed lookup, but lack obvious operations like listing all packages, publishing new ones, or updating existing registrations. Depending on the intended use case, this may be acceptable but leaves gaps for broader registry management.
Search and get install details on MCP servers, right from your agent -- a unified marketplace index.
Search, vet & assemble MCP servers from your agent: verified tools, risk labels, and trust scores.
Find an MCP server for any task: searches the official registry, Smithery and npm; remote-first.
Search and browse every MCP server in the Model Context Protocol registry.
