MCPVault

Name: MCPVault
Author: coburn2716

by coburn2716

Overview Schema Related Servers Score Discussions

TypeScript

Remote

MCPVault MCP Server

Search, inspect, and submit MCP servers from your AI agent. MCPVault exposes more than 18,000 records with evidence-labelled grades, freshness, verification, install, and compatibility data.

MCPVault

Install

No installation required. Run directly with npx:

npx -y mcpvault-mcp

Or install globally:

npm install -g mcpvault-mcp

Related MCP server: MCP Recommender

Client Configuration

Claude Desktop

Add to claude_desktop_config.json (typically ~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
  "mcpServers": {
    "mcpvault": {
      "command": "npx",
      "args": ["-y", "mcpvault-mcp"]
    }
  }
}

Claude Code

claude mcp add mcpvault -- npx -y mcpvault-mcp

Cursor

Add to your MCP configuration in Cursor settings:

{
  "mcpServers": {
    "mcpvault": {
      "command": "npx",
      "args": ["-y", "mcpvault-mcp"]
    }
  }
}

Tools

search_mcp_servers

Search the MCPVault directory by keyword, category, or status.

Parameters:

Parameter	Type	Required	Description
query	string	Yes	Search term, e.g. "postgres", "file system"
category	string	No	Filter by category, e.g. "Databases", "DevTools"
status	string	No	Filter by status: `verified`, `claimed`, or `stale`
limit	number	No	Results to return (default 10, max 30)

Example prompts:

"Find me a working postgres MCP server"
"Search for MCP servers in the DevTools category with status verified"
"What MCP servers are available for file system access?"

get_mcp_server

Retrieve full details for a specific server by its MCPVault slug.

Parameters:

Parameter	Type	Required	Description
slug	string	Yes	MCPVault slug visible in the listing URL: `mcpvault.io/servers/<slug>`

Returns: name, description, grade, status, verification date, GitHub repo, stars, license, client compatibility, topics, tool list, and listing URL.

Example prompts:

"Get details for the github MCP server"
"What clients does the postgres-mcp server support?"

get_install_command

Get the install command for a specific MCP server.

Parameters:

Parameter	Type	Required	Description
slug	string	Yes	MCPVault slug for the server

Returns the recorded install command and a link to the listing page. If no install command is on record, points to the listing for manual setup instructions.

Example prompts:

"How do I install the github MCP server?"
"What is the install command for filesystem-mcp?"

submit_mcp_server

Submit a GitHub repository to MCPVault as a new MCP server listing. If you find an MCP server on GitHub that is not yet in MCPVault, use this tool to add it. The repository is validated against the MCPVault plausibility gate (the repo name, description, or topics must mention "mcp" or "model context protocol"). Rate limited to 5 submissions per client per day.

Parameters:

Parameter	Type	Required	Description
repo_url	string	Yes	Full GitHub repository URL, e.g. `https://github.com/owner/repo`

Responses:

Submitted successfully: returns the listing URL and a note that the owner can claim it at mcpvault.io/claim.
Already listed: returns the existing listing URL.
Not an MCP server: explains what the plausibility gate checks.
Rate limited: try again tomorrow.

Example prompts:

"If you find an MCP server on GitHub that is not in MCPVault, submit it"
"Submit https://github.com/owner/my-mcp-server to MCPVault"
"Add this MCP server to MCPVault: https://github.com/owner/repo"

Evidence and limitations

verified means MCPVault completed a live MCP handshake at the recorded time. It is not a security audit.
Grades summarize repository activity, maintenance, documentation, and reliability signals. They are not sold and do not guarantee safety.
stale means the maintainer has not claimed the imported record. It does not mean the software is abandoned.
Install commands and compatibility data come from public metadata and maintainer edits. Review the linked repository before running third-party code.
This server sends search and submission requests to https://mcpvault.io. It does not read local files, credentials, prompts, or client conversations.

Support and security

For usage help, open an issue or contact hello@mcpvault.io. For a security concern, do not include secrets in a public issue. Email the same address with SECURITY in the subject.

See CHANGELOG.md for release notes.

About MCPVault

MCPVault is an independent directory of more than 18,000 MCP server records. Public evidence is labelled by source and timestamp. Claimed records are maintainer-controlled; verified records have passed a live MCP handshake.

Browse at mcpvault.io.

License

MIT. See LICENSE.

Available Tools

4 tools

get_install_commandA

Get the install command for a specific MCP server by its MCPVault slug. Returns the command to add it to your AI client, plus the listing URL.

ParametersJSON Schema

Name	Required	Description	Default
`slug`	Yes	MCPVault slug for the server.

TDQS

A4/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden. It communicates a read-only 'Get' action and discloses the return payload (command and listing URL), but it does not mention authentication, rate limits, or error behavior. This is adequate for a simple lookup but leaves some behavioral unknowns.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two concise sentences. The first states exactly what the tool does, and the second specifies the returned items. There is no redundant phrasing or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with one parameter and no output schema, the description covers the input (slug) and the output (command and listing URL). It does not explain what a MCPVault slug is or handle edge cases, but those are minor gaps given the simplicity of the tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the schema already describes slug as 'MCPVault slug for the server.' The description only repeats this concept ('by its MCPVault slug') without adding examples, format, or edge-case guidance, so it adds no real value beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Get the install command for a specific MCP server by its MCPVault slug.' This clearly distinguishes it from siblings like search_mcp_servers or submit_mcp_server, and the return content ('command... plus the listing URL') is explicitly stated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description establishes a clear usage context: when you have a specific MCPVault slug and need the install command. While it doesn't name alternatives or state when not to use it, the purpose is narrow enough that an agent can infer when to call it versus searching or submitting servers.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_mcp_serverA

Retrieve full details for a specific MCP server by its MCPVault slug. Includes grade, verification status, repo, stars, license, client compatibility, topics, and tool list.

ParametersJSON Schema

Name	Required	Description	Default
`slug`	Yes	MCPVault slug, e.g. 'postgres-mcp' or 'github'. Visible in the listing URL: mcpvault.io/servers/<slug>.

TDQS

A4.2/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the transparency burden. It clearly communicates that this is a read-only retrieval operation and discloses the fields returned. It does not mention error behavior or auth requirements, but for a simple lookup tool this is a minor gap rather than a serious omission.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that front-loads the action and resource, then efficiently lists the returned fields. Every element adds value and there is no filler or redundant restating of the tool name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple one-parameter retrieval tool, the description is adequately complete: it names the input and the expected result fields. It does not specify behavior for a nonexistent slug, but that is not essential for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema already documents the slug parameter thoroughly with examples and a listing URL. The description adds no additional parameter-specific semantics, so the baseline score of 3 for high schema coverage is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb ('Retrieve'), a specific resource ('a specific MCP server'), and the key identifier ('MCPVault slug'). It also enumerates the returned details, which clearly distinguishes it from the sibling search_mcp_servers, get_install_command, and submit_mcp_server.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'By its MCPVault slug' gives clear context for when to use this tool: when you already know the slug and need full details. It does not explicitly say to use search_mcp_servers when the slug is unknown, so the when-not/alternative guidance is left implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_mcp_serversB

Search the MCPVault directory for MCP servers. Returns name, grade, status, star count, description, and listing URL for each result.

ParametersJSON Schema

Name	Required	Description
`limit`	No	Number of results to return (default 10, max 30).
`query`	Yes	Search query, e.g. 'postgres', 'github', 'file system'.
`status`	No	Optional status filter: verified, claimed, or stale.
`category`	No	Optional category filter, e.g. 'Databases', 'DevTools', 'AI'.

TDQS

B3.4/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of behavioral disclosure. It does convey the action and return fields, indicating a read-only search operation. However, it does not mention which fields the query matches against, ordering, authentication needs, or behavior when no results are found, leaving notable ambiguity.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that front-loads the action and then compactly lists the return fields. There is no redundant wording; it is appropriately sized and to the point.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a four-parameter search tool with full schema documentation, the description is largely sufficient: it states the action and the returned shape. It lacks explicit sibling differentiation and detail on search semantics, but these gaps are minor given the schema's completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and all four parameters have clear descriptions in the schema. The tool description adds no parameter-specific semantics beyond what the schema already provides, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ("Search the MCPVault directory for MCP servers") and lists the returned fields (name, grade, status, star count, description, listing URL), clearly identifying it as a list/search operation. However, it does not explicitly differentiate from sibling tools like get_mcp_server or submit_mcp_server, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given about when to use this tool versus alternatives. The verb 'search' implies its purpose, but the description never states 'use get_mcp_server for a single server's details' or any other selection criteria. With three siblings present, this lack of routing leaves the agent to infer the right choice.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

submit_mcp_serverA

Submit a GitHub repository to the MCPVault directory as a new MCP server listing. Use this when you find an MCP server on GitHub that is not yet in MCPVault.

ParametersJSON Schema

Name	Required	Description	Default
`repo_url`	Yes	Full GitHub repository URL, e.g. https://github.com/owner/repo

TDQS

A3.7/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of disclosing behavior. 'Submit... as a new MCP server listing' implies a mutation, but it does not state any side effects, prerequisites like authentication, whether this opens a PR or directly modifies the directory, whether a duplicate is rejected, or what the response will be. This is a significant gap for a write operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences with no filler. The core action is front-loaded and the usage guidance is appended efficiently, making it easy for an agent to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple with one parameter, so the description covers purpose and usage adequately. However, with no output schema and no annotations, the agent is left without knowing what happens after submission or what the return value means. This incomplete behavioral context lowers the score.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% because the single parameter has a full description with an example. The tool description only repeats 'GitHub repository' and adds no meaning beyond the schema, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Submit') and names the exact resource ('GitHub repository to the MCPVault directory as a new MCP server listing'). This clearly distinguishes it from the sibling read/search tools because it is the only one that creates a listing.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Use this when you find an MCP server on GitHub that is not yet in MCPVault' provides an explicit condition for use. The 'not yet in MCPVault' phrase implies the negative case, but it does not explicitly name alternative sibling tools such as search_mcp_servers or get_mcp_server for checking existence.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

4 tool updatesv0.2.2Aug 30, 2026
- First observedget_install_command
- First observedget_mcp_server
- First observedsearch_mcp_servers
- First observedsubmit_mcp_server

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4/5.0

Disambiguation5/5

Each tool has a clearly distinct purpose: searching the directory, fetching full details, retrieving an install command, and submitting a new server. There is minimal overlap between search results and full details, and the install command is a separate concern.

Naming Consistency5/5

All tool names follow a consistent snake_case verb_noun pattern: search_mcp_servers, get_mcp_server, get_install_command, submit_mcp_server. The verbs and objects clearly indicate what each tool does.

Tool Count5/5

Four tools is well-scoped for a directory service: search, retrieve details, get install command, and submit. Each tool earns its place without redundancy or bloat.

Completeness4/5

The core workflow is covered: discover servers, view details, get install instructions, and submit new ones. Minor gaps like listing all servers without a search query or managing existing submissions are not critical for the stated purpose.

Maintenance

ActivityMaintained

ResponsivenessUnresponsive

Resources

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Find MCP - Agentage MCP Directory A
io.agentage
Search the official MCP registry: 17,000+ servers with trust grades, stars, tools, install config.
Search Developer Tools Documentation Access
32
MCP Finder B
io.github.c5huracan
Find the right MCP server for your task. 4,500+ servers ranked by community trust.
Search Developer Tools
3
MCP Marketplace A
io.mcp-marketplace
Search and install 4,000+ security-scanned MCP servers from inside any MCP-aware AI client.
Developer Tools Search
72
MCP Toplist A
com.mcptoplist
Search 77,000+ MCP servers ranked by real adoption data to find the right one for any task.
Search Developer Tools
23

Related MCP Servers

mcp-registry-server
Search RAG Systems
KBB99
A
license
C
quality
D
maintenance
Easily find MCP servers using our MCP registry. Search with natural language.
Updated 2 years ago (2025-02-05 23:18 UTC)
1
5
MIT
MCP Recommender
Developer Tools Search RAG Systems
bxzymy
A
license
A
quality
D
maintenance
Provides intelligent recommendations for MCP servers based on development needs using natural language queries. Searches through 874+ curated MCP servers across 36+ categories with advanced matching algorithms.
Updated a year ago (2025-08-31 02:16 UTC)
3
5
MIT
loaditout-mcp-serverofficial
Developer Tools Search
loaditoutadmin
A
license
A
quality
D
maintenance
MCP server for discovering and installing AI agent skills from Loaditout. Search 20,000+ security-gradedMCP servers, check A/B/C/F grades, get install configs, and browse trending skills and curated packs.
Updated 5 months ago (2026-04-07 11:24 UTC)
21
56
1
MIT
beacon-mcp
AI & Machine Learning Developer Tools Search
enrichgateagent-png
A
license
A
quality
A
maintenance
MCP server that searches 3,800+ open-source AI agents by capability, ranked by real traction (stars, activity). Query it from Claude Desktop, Cursor, Cline, or Windsurf.
Updated 2 months ago (2026-07-13 17:16 UTC)
3
61
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/coburn2716/mcpvault-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

MCPVault MCP Server

Install

Client Configuration

Claude Desktop

Claude Code

Cursor

Tools

search_mcp_servers

get_mcp_server

get_install_command

submit_mcp_server

Evidence and limitations

Support and security

About MCPVault

License

Available Tools

Tool Schema Changelog

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

loaditout-mcp-serverofficial

Latest Blog Posts

MCP directory API