Skip to main content
Glama
KB01111

auth-mcp

by KB01111
OverviewSchemaRelated ServersScoreDiscussions
Python
Hybrid

auth-mcp

A secure MCP server that stores all your API keys and auth credentials in one place, retrievable by any MCP client (Goose, Claude Code, Cursor, Codex, Gemini CLI...). Built with FastMCP so it can be hosted on Prefect Horizon and reached over HTTP at a URL like https://<name>.fastmcp.app/mcp.

Features

Tool

Description

auth_set(name, value, description)

Store or update a credential

auth_get(name, mask=True)

Retrieve a credential (masked by default; mask=False for full value)

auth_list()

List names + metadata only — never values

auth_search(query)

Search by name/description — metadata only

auth_recommend(task)

MCP sampling — asks goose's AI to pick the best credential for a task

auth_delete(name)

Delete a credential

auth_health()

Health check

Related MCP server: MCP-Secrets-Vault

Security model

  • Encrypted at rest — the file backend encrypts every value with Fernet (AES-128-CBC + HMAC), key derived from AUTH_MCP_MASTER_KEY via PBKDF2-HMAC-SHA256 (600k iterations). The vault file never contains a plaintext secret.

  • List/search never leak values — only names, descriptions and timestamps.

  • Masked by default — auth_get returns ********last4 unless you explicitly pass mask=False.

  • Remote access is authenticated by the hosting platform (FastMCP/Prefect Horizon).

  • Optional prefect backend stores secrets as Prefect Cloud Secret blocks (durable, encrypted at rest by Prefect, RBAC-scoped) — ideal for the hosted deployment.

MCP sampling

auth_recommend(task) uses MCP sampling: the server sends the task plus a list of available credentials (names + descriptions only — values never leave the vault) back to goose's LLM, which returns the single best match and its reasoning. This turns the vault into a smart credential router:

auth_recommend(task="call OpenAI to summarize this email thread")
# -> {"ok": true, "recommendation": "openai",
#     "reasoning": "Task mentions OpenAI summarization.", "available": [...]}
# then:  auth_get(name="openai", mask=False)

Sampling is automatically available in goose (no configuration needed) and gracefully degrades — if the client doesn't support sampling, the tool returns the full list instead.

⚠️ Never commit .env, the vault file, or real keys. Everything sensitive is git-ignored.

Project layout

auth-mcp/
├── pyproject.toml            # deps + entry point (also used as Horizon "requirements")
├── README.md
├── .env.example              # copy to .env and fill in
├── src/auth_mcp/
│   ├── config.py             # env config (backend, master key, vault path)
│   ├── storage.py            # EncryptedFileStore + PrefectSecretStore backends
│   └── server.py             # FastMCP server + tools (Horizon server path)
└── tests/test_storage.py

Run locally

cd auth-mcp
python -m venv .venv
.venv\Scripts\activate            # Windows  (macOS/Linux: source .venv/bin/activate)
pip install -e ".[test]"

# generate a master key and run the server
set AUTH_MCP_MASTER_KEY=CHANGE-ME-strong-passphrase
python -m auth_mcp.server

Test it:

pytest -q

The server speaks MCP over stdio. Add it to your local Goose/Claude Code/Cursor config, then try:

auth_set(name="openai", value="sk-...", description="OpenAI API key")
auth_list()
auth_get(name="openai")            # -> ********1234
auth_get(name="openai", mask=False)

Deploy to Prefect Horizon

Prefect Horizon hosts FastMCP servers directly from a GitHub repo. Steps:

  1. Push this project to GitHub

    cd auth-mcp
git init && git add . && git commit -m "Initial auth-mcp"
# create a repo on github.com and:
git remote add origin git@github.com:<you>/auth-mcp.git
git push -u origin main

  2. Sign in to horizon.prefect.io (create an account if needed).

  3. Create a new server and point it at your repo:

    • Repository: <you>/auth-mcp

    • Server path: src/auth_mcp/server.py

    • Requirements: pyproject.toml

  4. Set environment variables in the Horizon UI:

    Variable

    Value

    AUTH_MCP_MASTER_KEY

    A strong passphrase (see below)

    AUTH_MCP_BACKEND

    prefect (recommended for hosted: secrets live in Prefect Cloud)

    PREFECT_API_URL

    https://api.prefect.cloud/api/accounts/<ACCOUNT_ID>/workspaces/<WORKSPACE_ID>

    PREFECT_API_KEY

    A Prefect Cloud API key that can read/write Secret blocks

    Generate a master key:

    python -c "import secrets; print(secrets.token_urlsafe(32))"

  5. Deploy, then copy your server URL, e.g. https://auth-mcp-xxxx.fastmcp.app/mcp.

  6. Point your MCP client at the URL (HTTP transport):

    • Goose: goose mcp add auth-mcp --transport http https://auth-mcp-xxxx.fastmcp.app/mcp

    • Claude Code: claude mcp add auth-mcp --transport http https://auth-mcp-xxxx.fastmcp.app/mcp

    • Cursor: add to .cursor/mcp.json with "url": "https://auth-mcp-xxxx.fastmcp.app/mcp"

    Any client on your team can now read/write shared credentials through one hosted endpoint.

Backends

  • file (default): encrypted vault on disk (AUTH_MCP_VAULT_PATH, default .auth_vault.json). Zero external services; good for local use and simple self-hosting.

  • prefect: each credential is a Prefect Secret block. Install with pip install "auth-mcp[prefect]". Requires PREFECT_API_URL + PREFECT_API_KEY. Best for the Horizon deployment since secrets survive restarts and are managed by Prefect Cloud.

Security checklist

  • Use a long, unique AUTH_MCP_MASTER_KEY and store it in a password manager

  • Never commit .env or *.json vault files

  • Grant the Horizon/Prefect API key only the permissions it needs (Secret blocks)

  • Rotate keys regularly (auth_set overwrites in place)

  • Keep mask=True unless a full value is genuinely required

Available Tools

7 tools
auth_deleteA

Permanently delete a credential from the vault.

Args: name: Credential name.

Returns: Confirmation.

ParametersJSON Schema
NameRequiredDescriptionDefault
nameYes

Output Schema

ParametersJSON Schema
NameRequiredDescription

No output parameters

TDQS

A3.8/5.0
Behavior3/5

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

The description explicitly says 'permanently delete,' disclosing the destructive and irreversible nature of the operation. It also states the return type (confirmation). However, with no annotations, it lacks additional behavioral context such as required permissions or error behavior.

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 concise and well-structured with an Args/Returns format. Every sentence adds value, and the purpose is front-loaded.

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 delete operation with one parameter, the description covers the essential elements: action, parameter meaning, and return value. It lacks potential error scenarios, but given the tool's simplicity, it is reasonably complete.

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

Parameters4/5

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

Schema coverage is 0%, so the description must compensate. It explains the single parameter 'name' as 'Credential name,' which clarifies the semantics beyond the bare schema. For a simple one-parameter tool, this is adequate.

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 clearly states the action (permanently delete) and the resource (a credential from the vault). This distinguishes it from sibling tools like auth_set, auth_list, and auth_get.

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 on when to use this tool versus alternatives. It does not mention prerequisites, such as the credential needing to exist, nor does it explain when to prefer delete over other auth tools.

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

auth_getA

Retrieve a credential value.

Args: name: Credential name. mask: If True (default), return a masked form (********last4). Set to False to get the full value.

Returns: The credential value (masked or full).

ParametersJSON Schema
NameRequiredDescriptionDefault
maskNo
nameYes

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.4/5.0
Behavior4/5

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

No annotations are provided, so the description carries the burden of disclosure. It explicitly describes the masking default behavior and the ability to retrieve the full value, which goes beyond the schema. It does not mention error handling or permissions, but the core behavioral trait is well covered.

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 tidy docstring with a one-sentence summary, an Args section, and a Returns section. Every sentence is informative, with no redundancy or filler, making it efficient and easy to parse.

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?

Given the presence of an output schema, the description does not need to detail return types. It covers the primary behavior (retrieval with masking) and parameter semantics sufficiently. It lacks discussion of edge cases like missing credentials, but the overall context is complete for a simple retrieval tool.

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

Parameters4/5

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

Schema description coverage is 0%, so the description must compensate. It provides a clear explanation for 'name' (Credential name) and thoroughly explains the 'mask' parameter, including the default and the resulting masked format. This adds significant meaning beyond the raw 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 starts with 'Retrieve a credential value,' which is a specific verb and resource, clearly distinguishing it from siblings like auth_list (listing) and auth_search (searching). It also explains the mask behavior, further clarifying its purpose.

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 clearly indicates this tool is for retrieving a single credential by name, and explains the mask option. It does not explicitly name alternatives or exclusions, but the context is unambiguous given the sibling tool names.

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

auth_healthA

Health check for the auth-mcp server.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

Output Schema

ParametersJSON Schema
NameRequiredDescription

No output parameters

TDQS

A3.9/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden. It only states 'Health check' without disclosing what the check entails, whether it is read-only, what information it returns, or if any side effects exist. This leaves significant ambiguity about the tool's behavior.

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, concise sentence that front-loads the purpose with no unnecessary words. It earns its place perfectly.

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?

Given the tool's simplicity (zero params, output schema present), the description is minimally viable but lacks detail about what 'health' means (e.g., connectivity, uptime) or how the result should be interpreted. The output schema may cover return values, but the description doesn't reference it, leaving the agent to guess.

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

Parameters4/5

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

The tool has zero parameters, and the schema coverage is 100% (empty schema). Per baseline rules, a 4 is appropriate since there are no parameter semantics to convey beyond what the schema already provides.

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 clearly states the tool's purpose: a health check for the auth-mcp server. The verb 'check' and resource 'auth-mcp server' are specific, and it distinguishes itself from sibling auth operation tools by focusing on health status.

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 implies when to use: when needing to verify the health of the auth-mcp server. While it doesn't explicitly compare to siblings, the context is clear that this is a diagnostic tool, distinct from the operational auth tools listed.

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

auth_listA

List all stored credentials (names + metadata only, never values).

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations provided, the description carries the full burden. It explicitly discloses that values are never returned, which is a critical behavioral safety trait. It does not cover prerequisites or side effects, but for a read-only list operation, the key transparency is addressed.

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, front-loaded sentence that is information-dense and free of extraneous words. Every part adds value: action, scope, content list, and exclusion of secrets.

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

Completeness5/5

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

Given the tool's simplicity, zero parameters, and existence of an output schema, the description fully covers the essential context. It tells the agent what to expect (names and metadata, not values) without over-explaining, leaving return format details to the output schema.

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

Parameters4/5

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

The tool takes zero parameters, and the schema is fully covered by having no properties. The description adds meaningful context about what is included (names + metadata) and excluded (values), going beyond the minimal baseline for parameterless tools.

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 clearly states a specific action ('List all stored credentials') with a clear scope (all) and content boundary (names + metadata only). This distinguishes it from siblings like auth_get, auth_search, and auth_delete, making the purpose unambiguous.

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 clearly indicates this tool is for listing all credentials, which implies its use case versus alternatives like auth_search or auth_get. However, there is no explicit mention of when not to use it or alternative tools, leaving it slightly below the highest bar.

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

auth_recommendA

Ask goose's AI to pick the best stored credential for a task.

This tool uses MCP sampling: it sends the task plus the list of available credentials (names + descriptions only — values never leave the vault) back to goose's LLM, which returns the single best match and the reasoning. Retrieve the value afterwards with auth_get(name, mask=False).

If the client does not support sampling, the tool degrades gracefully and returns the full list so the caller can choose manually.

Args: task: What the credential will be used for, e.g. "call OpenAI to summarize this email thread".

Returns: recommendation (credential name or None), reasoning, and available (all credential names).

ParametersJSON Schema
NameRequiredDescriptionDefault
taskYes

Output Schema

ParametersJSON Schema
NameRequiredDescription

No output parameters

TDQS

A4.7/5.0
Behavior5/5

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

With no annotations provided, the description fully carries the burden of behavioral disclosure. It clearly states that values never leave the vault, that it uses MCP sampling, that it sends only names and descriptions to the LLM, and that it degrades gracefully to returning the full list. This is comprehensive for a read-only recommendation tool.

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

Conciseness4/5

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

The description is well-structured with a summary, mechanism, fallback behavior, and Args/Returns sections. It is slightly longer than absolutely necessary but every sentence adds value, and the structure makes it easy to scan.

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

Completeness5/5

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 a non-trivial output shape, the description fully covers the return fields (recommendation, reasoning, available), the security model, and the graceful degradation path. It is complete given the complexity and lack of annotations.

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

Parameters5/5

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

The single parameter 'task' has no schema description (0% coverage), so the tool description must compensate. It does so effectively with 'What the credential will be used for' and a concrete example, adding meaning beyond the bare schema definition.

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 clear, specific statement: 'Ask goose's AI to pick the best stored credential for a task.' This distinguishes it from sibling tools like auth_get (which retrieves values) and auth_search (which searches), and it explains the unique AI-driven selection mechanism.

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 provides context for use ('when you need to pick the best credential for a task') and explicitly tells the caller to retrieve the value afterward with auth_get. It also describes graceful degradation when sampling is unsupported, but does not explicitly exclude alternatives or provide when-not-to-use guidance.

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

auth_setA

Create or update an API key / credential in the vault.

Args: name: Unique name for the credential, e.g. "openai" or "stripe-live". value: The secret value (API key, token, password...). Never echoed back. description: Optional human-readable note shown in listings.

Returns: Metadata for the saved credential (with a masked preview only).

ParametersJSON Schema
NameRequiredDescriptionDefault
nameYes
valueYes
descriptionNo

Output Schema

ParametersJSON Schema
NameRequiredDescription

No output parameters

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations provided, the description carries the full transparency burden. It discloses that the value is never echoed back and that only masked metadata is returned, which is important security behavior. However, it does not specify error handling, idempotency, or prerequisites, so it is not fully comprehensive.

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 tightly organized with separate sections for Args and Returns, using short lines and no redundant text. Each sentence adds value, and the format makes it easy to scan and parse.

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?

With 3 parameters, an output schema present, and no annotations, the description provides enough to select and use the tool correctly. It covers purpose, argument semantics, and return behavior. It omits edge-case behavior like what happens if a name already exists, but that is minor given the 'create or update' phrasing.

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

Parameters5/5

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

Schema description coverage is 0% (no parameter descriptions in schema), so the description is the sole source of parameter semantics. It provides meaningful details: name is unique with examples, value is secret and not echoed, description is optional and used for human-readable notes. This far exceeds the schema's bare type definitions.

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 clearly states 'Create or update an API key / credential in the vault' which is a specific verb (create/update) with a resource (API key/credential) and location (vault). This distinguishes it from siblings like auth_list, auth_get, and auth_delete that have different actions.

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 implies usage for storing new credentials or updating existing ones, but it does not explicitly name alternatives or exclusions such as 'use auth_get to retrieve' or 'do not use for deletion'. Clear context is provided, but no when-not guidance.

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.

  1. 7 tool updatesv0.1.0
    • First observedauth_delete
    • First observedauth_get
    • First observedauth_health
    • First observedauth_list
    • First observedauth_recommend
    • First observedauth_search
    • First observedauth_set
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A4.4/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose: set (create/update), get (retrieve value), list (enumerate metadata), search (query metadata), delete (remove), recommend (AI selection), and health (server status). No two tools perform the same action; even the related list/search/recommend are distinguished by their inputs and outputs.

Naming Consistency5/5

All tools follow a consistent 'auth_<verb>' pattern (set, list, search, recommend, delete, get, health). The verb is always lowercase and after the namespace prefix, making the tool set predictable and easy to navigate.

Tool Count5/5

Seven tools is ideal for a credential vault: it covers the full lifecycle (create, read, update/delete, list/search) plus health and an AI recommendation feature. Every tool earns its place without redundancy or bloat.

Completeness5/5

The surface fully covers credential management: creation/updating (auth_set), retrieval (auth_get), listing (auth_list), searching (auth_search), deletion (auth_delete), and an intelligent selection helper (auth_recommend). No essential operation is missing, and the workflow between recommend and get is explicitly documented.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

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

Related MCP Connectors

Related MCP Servers

  • Janee

    rsdouglas
    A
    license
    Not graded
    quality
    C
    maintenance
    Secrets management MCP server that injects credentials into API requests for AI agents, enforcing policies and logging all activity without exposing raw keys.
    197
    30
    MIT

  • VaultMCP

    Axiler-Lab
    F
    license
    Not graded
    quality
    B
    maintenance
    An encrypted secret vault and MCP gateway that securely stores API keys and injects them into upstream MCP servers, so AI IDEs never see raw credentials.
    9
    -

  • AgentVault

    bch1212
    A
    license
    Not graded
    quality
    C
    maintenance
    MCP server for AI-native credential management, enabling agents to securely store, retrieve, and manage API keys with encryption, spending budgets, and audit logging.
    MIT

Latest Blog Posts

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/KB01111/auth-mcp'

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