Skip to main content
Glama
Pangolin MCP Connector

Pangolin MCP Connector

by si-essence

pangolin-mcp (Pangolin MCP connector)

MCP connector for a self-hosted Pangolin Community Edition Integration API. It speaks that REST API over stdio and over stateless Streamable HTTP on localhost.

Pangolin Community Edition is AGPL-3.0 software. This connector is MIT. It only calls the public Integration REST API on the server you configure. It is not affiliated with Fossorial or Pangolin. Bring your own API key from your self-hosted instance (org-scoped or root).

This connector covers all 234 paths and 305 operations in pangolin.openapi.json (Pangolin CE 1.25.3). Operations are grouped into 20 toolsets. Enable a subset with PANGOLIN_TOOLSETS so the model only sees the tools you need.

Self-hosted Community Edition only. There is no default base URL. PANGOLIN_URL is required and must be your Integration API origin, for example https://api.example.com or http://127.0.0.1:3003. A trailing /v1 is stripped. Calls go to {PANGOLIN_URL}/v1. Hosts on pangolin.net are refused.

Setup

npm install
npm run ci
npm start
npm run start:http

npm start speaks stdio. npm run start:http serves Streamable HTTP at http://127.0.0.1:3000/mcp and GET /health. HTTP mode has no authentication. Keep it on localhost.

Create an API key in Pangolin (org API keys, or a root key on CE). The connector sends it as Authorization: Bearer and never prints it.

{
  "mcpServers": {
    "pangolin": {
      "command": "node",
      "args": ["/workspace/connectors/pangolin/dist/index.js"],
      "env": {
        "PANGOLIN_URL": "http://127.0.0.1:3003",
        "PANGOLIN_API_KEY": "...",
        "PANGOLIN_ALLOW_WRITES": "false",
        "PANGOLIN_TOOLSETS": "sites,resources,targets,roles,users,orgs",
        "PANGOLIN_CONTACT": "you@example.com"
      }
    }
  }
}

Docker (HTTP, no authentication, localhost only):

docker build -t pangolin-mcp .
docker run -p 3000:3000 \
  -e PANGOLIN_URL=http://host.docker.internal:3003 \
  -e PANGOLIN_API_KEY=... \
  pangolin-mcp

Do not put the API key in the image.

Regenerate the operations registry after an OpenAPI bump:

npm run gen:operations

Related MCP server: si.sigit/cli

Config

Variable

Meaning

PANGOLIN_URL

Required. Self-hosted Integration API origin. /v1 is appended. Cloud hosts are refused.

PANGOLIN_API_KEY

API key. Sent as Authorization: Bearer.

PANGOLIN_ALLOW_WRITES

Must be the literal true before a confirmed write is sent.

PANGOLIN_TOOLSETS

Comma list of toolsets, or all. Default sites,resources,targets,roles,users,orgs.

PANGOLIN_PER_MINUTE

Local request budget. Default 30.

PANGOLIN_TIMEOUT_MS

Upstream timeout. Default 20000.

PANGOLIN_CACHE_TTL_SEC

GET cache TTL. Default 60. Writes clear the cache.

PANGOLIN_CONTACT

Contact token in the User-Agent.

MCP_TRANSPORT

stdio or http. --http overrides.

PORT

HTTP port. Default 3000.

Safety

GET operations, and POST or PUT ops whose summaries are list or get, run without confirm. Every other write is gated.

A write needs confirm: true and PANGOLIN_ALLOW_WRITES=true. Otherwise the tool returns a dry-run preview of the method, path, query, and body. Secrets are redacted. Extra preview warnings cover public resource exposure, share links and access tokens, rules, targets, deletes of org, site, resource, user, role, client, domain, IdP, or API key, API key create and action grants, user invites, auth and bypass changes, certificate restart, and blueprint apply.

Pangolin wraps JSON in { data, success, error, message, status }. The connector returns data, message, and pagination. It never returns stack or server filesystem paths. Field names apiKey, secret, token, password, newtSecret, olmSecret, accessToken, clientSecret, and other secret/token/password/key names are redacted. Id fields such as apiKeyId and orgId are kept.

HTTP 401 means the key was rejected. HTTP 403 means the key does not have that action granted. HTTP 400 and 422 are validation errors. HTTP 429 includes Retry-After.

Tools

Default PANGOLIN_TOOLSETS publishes 6 tools. PANGOLIN_TOOLSETS=all publishes 20 tools (305 operations). Each tool takes action plus params, query, body, and optional confirm.

Toolset

Tool

Operations

Tags

Default

sites

pangolin_sites

11

Site

yes

resources

pangolin_resources

123

Public Resource, Public Resource (Legacy), Private Resource, Private Resource (Legacy)

yes

targets

pangolin_targets

3

Resource Target

yes

roles

pangolin_roles

6

Role

yes

users

pangolin_users

12

User, User Invitation

yes

orgs

pangolin_orgs

10

Organization

yes

domains

pangolin_domains

5

Domain

no

clients

pangolin_clients

17

Client

no

policies

pangolin_policies

37

Public Resource Policy, Public Resource Policy (Legacy)

no

access_tokens

pangolin_access_tokens

2

Access Token

no

identity_providers

pangolin_identity_providers

9

Identity Provider (Global)

no

api_keys

pangolin_api_keys

5

API Key

no

blueprints

pangolin_blueprints

3

Blueprint

no

logs

pangolin_logs

10

Logs

no

labels

pangolin_labels

6

Label

no

certificates

pangolin_certificates

2

Certificate

no

redirects

pangolin_redirects

6

Redirect

no

ai

pangolin_ai

34

AI Provider, AI Model, AI Budget, Virtual API Key

no

remote_exit_nodes

pangolin_remote_exit_nodes

1

Remote Exit Node

no

meta

pangolin_meta

3

Health Check, OpenAPI

no

Example. List orgs, then create one after previewing:

{ "action": "list_orgs" }
{ "action": "create_org", "body": { "orgId": "lab", "name": "Lab", "subnet": "100.90.128.0/24", "utilitySubnet": "192.0.2.0/24" } }
{ "action": "create_org", "body": { "orgId": "lab", "name": "Lab", "subnet": "100.90.128.0/24", "utilitySubnet": "192.0.2.0/24" }, "confirm": true }

Live check

npm run live-check talks to a real Pangolin CE when PANGOLIN_URL and PANGOLIN_API_KEY are set. It lists orgs, creates a throwaway org (preview then confirm), then creates, reads, updates, and deletes a site, a role, and a public resource with a target where the CE API allows it. It lists users, domains, API keys, and logs, then deletes the org. If those variables are unset, it prints a skip message and exits 0.

LIVE-CHECK.md records the real run against Pangolin CE 1.25.3 built from source on the box.

Attribution

Pangolin is AGPL-3.0 (Community Edition). This connector is MIT and is not a derivative of Pangolin source. It is an independent HTTP client of the Integration API.

License

MIT, see LICENSE. This is an independent, unofficial connector and is not endorsed by the Pangolin project or its owners.

The upstream pangolin.openapi.json comes from a AGPL-3.0 project, so it is not shipped here. src/operations.ts was generated from it, and tests fall back to a route-only fixture in test/fixtures/. To regenerate, download the spec from the upstream project into the repo root (it is gitignored) and run node scripts/gen-operations.mjs.

Available Tools

6 tools
pangolin_orgsA
DestructiveIdempotent

pangolin_orgs covers the orgs toolset (10 operations). Auth header Authorization Bearer. Self-hosted Pangolin CE only. Writes need confirm:true and PANGOLIN_ALLOW_WRITES=true. Omit confirm for a dry-run preview. Actions: check_org_user: GET /org/{orgId}/user/{userId}/check. Check a user's access in an organization. create_org: PUT /org. Create a new organization delete_admin_org: DELETE /admin/org/{orgId}. Delete any organization in the system (server admin). delete_org: DELETE /org/{orgId}. Delete an organization get_org: GET /org/{orgId}. Get an organization list_admin_orgs: GET /admin/orgs. List all organizations in the system with usage counts (server admin). list_orgs: GET /orgs. List all organizations in the system. reset_org_bandwidth: POST /org/{orgId}/reset-bandwidth. Reset all sites in selected organization bandwidth counters. update_org: POST /org/{orgId}. Update an organization update_org_user: POST /org/{orgId}/user/{userId}. Update a user in an org.

Inputs: action (required), body, query, params, +1 more.

pangolin_resourcesA
DestructiveIdempotent

pangolin_resources covers the resources toolset (123 operations). Auth header Authorization Bearer. Self-hosted Pangolin CE only. Writes need confirm:true and PANGOLIN_ALLOW_WRITES=true. Omit confirm for a dry-run preview. Actions: add_client_site_resources: POST /client/{clientId}/site-resources. Add a machine client to multiple site resources at once. add_private_resource_clients: POST /private-resource/{resourceId}/clients/add. Add a single client to a site resource. Clients with a userId cannot be added. add_private_resource_roles: POST /private-resource/{resourceId}/roles/add. Add a single role to a site resource. add_private_resource_users: POST /private-resource/{resourceId}/users/add. Add a single user to a site resource. add_public_resource_roles: POST /public-resource/{resourceId}/roles/add. Add a single role to a resource. When the resource has an inline policy defined (no shared resource policy assigned), the role is added to the inline policy instead of directly to the resource. add_public_resource_users: POST /public-resource/{resourceId}/users/add. Add a single user to a resource. When the resource has an inline policy defined (no shared resource policy assigned), the user is added to the inline policy instead of directly to the resource. add_public_resource_whitelist: POST /public-resource/{resourceId}/whitelist/add. Add a single email to the resource whitelist. add_resource_ai_models: POST /resource/{resourceId}/ai-models/add. Add a single model to an inference resource allow/block selection. Requires at least one attached AI provider in select mode. The model must belong to a select-mode provider and its listType must match the provider catalog entry. listType defaults to allow. add_resource_ai_providers: POST /resource/{resourceId}/ai-providers/add. Add or replace a single AI provider attachment on an inference resource. The provider is attached in inherit mode, using its own allow/block lists. add_resource_roles: POST /resource/{resourceId}/roles/add. Add a single role to a resource. When the resource has an inline policy defined (no shared resource policy assigned), the role is added to the inline policy instead of directly to the resource. add_resource_users: POST /resource/{resourceId}/users/add. Add a single user to a resource. When the resource has an inline policy defined (no shared resource policy assigned), the user is added to the inline policy instead of directly to the resource. add_resource_whitelist: POST /resource/{resourceId}/whitelist/add. Add a single email to the resource whitelist. add_site_resource_ai_models: POST /site-resource/{siteResourceId}/ai-models/add. Add a single model to an inference site resource allow/block selection. Requires at least one attached AI provider in select mode. The model must belong to a select-mode provider and its listType must match the provider catalog entry. listType defaults to allow. add_site_resource_ai_providers: POST /site-resource/{siteResourceId}/ai-providers/add. Add or replace a single AI provider attachment on an inference site resource. The provider is attached in inherit mode, using its own allow/block lists. add_site_resource_clients: POST /site-resource/{siteResourceId}/clients/add. Add a single client to a site resource. Clients with a userId cannot be added. add_site_resource_roles: POST /site-resource/{siteResourceId}/roles/add. Add a single role to a site resource. add_site_resource_users: POST /site-resource/{siteResourceId}/users/add. Add a single user to a site resource. create_org_private_resource: PUT /org/{orgId}/private-resource. Create a new site resource. create_org_public_resource: PUT /org/{orgId}/public-resource. Create a resource. create_org_resource: PUT /org/{orgId}/resource. Create a resource. create_org_site_resource: PUT /org/{orgId}/site-resource. Create a new site resource. create_public_resource_access_token: POST /public-resource/{resourceId}/access-token. Generate a new access token for a resource. create_public_resource_mtls_certificate: PUT /public-resource/{resourceId}/mtls/certificate. Add a trusted CA certificate that clients must present a certificate signed by when mTLS is enabled on a resource. Accepts a PEM bundle; each certificate in the bundle is stored separately. When no shared resource policy is assigned, this updates the resource's inline policy. create_public_resource_rule: PUT /public-resource/{resourceId}/rule. Create a resource rule. create_public_resource_target: PUT /public-resource/{resourceId}/target. Create a target for a resource. create_resource_access_token: POST /resource/{resourceId}/access-token. Generate a new access token for a resource. create_resource_mtls_certificate: PUT /resource/{resourceId}/mtls/certificate. Add a trusted CA certificate that clients must present a certificate signed by when mTLS is enabled on a resource. Accepts a PEM bundle; each certificate in the bundle is stored separately. When no shared resource policy is assigned, this updates the resource's inline policy. create_resource_rule: PUT /resource/{resourceId}/rule. Create a resource rule. create_resource_target: PUT /resource/{resourceId}/target. Create a target for a resource. delete_private_resource: DELETE /private-resource/{siteResourceId}. Delete a site resource. delete_public_resource: DELETE /public-resource/{resourceId}. Delete a resource. delete_public_resource_mtls_certificate: DELETE /public-resource/{resourceId}/mtls/certificate/{mtlsCertificateId}. Remove a trusted CA certificate from a resource. If it is the last one, mTLS is disabled on the resource since it can no longer verify any client. When no shared resource policy is assigned, this updates the resource's inline policy. delete_public_resource_rule: DELETE /public-resource/{resourceId}/rule/{ruleId}. Delete a resource rule. delete_resource: DELETE /resource/{resourceId}. Delete a resource. delete_resource_mtls_certificate: DELETE /resource/{resourceId}/mtls/certificate/{mtlsCertificateId}. Remove a trusted CA certificate from a resource. If it is the last one, mTLS is disabled on the resource since it can no longer verify any client. When no shared resource policy is assigned, this updates the resource's inline policy. delete_resource_rule: DELETE /resource/{resourceId}/rule/{ruleId}. Delete a resource rule. delete_site_resource: DELETE /site-resource/{siteResourceId}. Delete a site resource. get_org_resource: GET /org/{orgId}/resource/{niceId}. Get a resource by orgId and niceId. NiceId is a readable ID for the resource and unique on a per org basis. get_org_site_resource_nice: GET /org/{orgId}/site/{siteId}/resource/nice/{niceId}. Get a specific site resource by niceId. get_private_resource: GET /private-resource/{siteResourceId}. Get a specific site resource by siteResourceId. get_public_resource: GET /public-resource/{resourceId}. Get a resource by resourceId. get_public_resource_policies: GET /public-resource/{resourceId}/policies. Get the inline and shared policies associated with a resource. get_public_resource_whitelist: GET /public-resource/{resourceId}/whitelist. Get the whitelist of emails for a specific resource. get_resource: GET /resource/{resourceId}. Get a resource by resourceId. get_resource_blueprint: GET /resource/{resourceId}/blueprint. Generate a blueprint YAML snippet that recreates this resource. get_resource_policies: GET /resource/{resourceId}/policies. Get the inline and shared policies associated with a resource. get_resource_whitelist: GET /resource/{resourceId}/whitelist. Get the whitelist of emails for a specific resource. get_site_resource: GET /site-resource/{siteResourceId}. Get a specific site resource by siteResourceId. get_site_resource_blueprint: GET /site-resource/{siteResourceId}/blueprint. Generate a blueprint YAML snippet that recreates this site resource. list_org_private_resources: GET /org/{orgId}/private-resources. List all site resources for an organization. list_org_public_resource_names: GET /org/{orgId}/public-resource-names. List all resource names for an organization. list_org_public_resources: GET /org/{orgId}/public-resources. List resources for an organization. list_org_resources: GET /org/{orgId}/resources. List resources for an organization. list_org_resources_names: GET /org/{orgId}/resources-names. List all resource names for an organization. list_org_site_private_resources: GET /org/{orgId}/site/{siteId}/private-resources. List site resources for a site. list_org_site_resources: GET /org/{orgId}/site/{siteId}/resources. List site resources for a site. list_org_site_resources_org_id: GET /org/{orgId}/site-resources. List all site resources for an organization. list_private_resource_clients: GET /private-resource/{resourceId}/clients. List all clients for a site resource. list_private_resource_roles: GET /private-resource/{resourceId}/roles. List all roles for a site resource. list_private_resource_users: GET /private-resource/{resourceId}/users. List all users for a site resource. list_public_resource_access_tokens: GET /public-resource/{resourceId}/access-tokens. List all access tokens for a resource. list_public_resource_mtls_certificates: GET /public-resource/{resourceId}/mtls/certificates. List the trusted CA certificates for a resource's mTLS. When no shared resource policy is assigned, these are the resource's inline policy certificates. list_public_resource_roles: GET /public-resource/{resourceId}/roles. List all roles for a resource. list_public_resource_rules: GET /public-resource/{resourceId}/rules. List rules for a resource. list_public_resource_targets: GET /public-resource/{resourceId}/targets. List targets for a resource. list_public_resource_users: GET /public-resource/{resourceId}/users. List all users for a resource. list_resource_access_tokens: GET /resource/{resourceId}/access-tokens. List all access tokens for a resource. list_resource_ai_models: GET /resource/{resourceId}/ai-models. List the models this resource has selected from its select-mode providers' allow/block lists. Providers in inherit mode are not represented here; they use their own lists. list_resource_ai_providers: GET /resource/{resourceId}/ai-providers. List AI providers attached to an inference resource, including each attachment's accessMode. list_resource_mtls_certificates: GET /resource/{resourceId}/mtls/certificates. List the trusted CA certificates for a resource's mTLS. When no shared resource policy is assigned, these are the resource's inline policy certificates. list_resource_roles: GET /resource/{resourceId}/roles. List all roles for a resource. list_resource_rules: GET /resource/{resourceId}/rules. List rules for a resource. list_resource_targets: GET /resource/{resourceId}/targets. List targets for a resource. list_resource_users: GET /resource/{resourceId}/users. List all users for a resource. list_site_resource_ai_models: GET /site-resource/{siteResourceId}/ai-models. List the models this site resource has selected from its select-mode providers' allow/block lists. Providers in inherit mode are not represented here; they use their own lists. list_site_resource_ai_providers: GET /site-resource/{siteResourceId}/ai-providers. List AI providers attached to an inference site resource, including each attachment's accessMode. list_site_resource_clients: GET /site-resource/{siteResourceId}/clients. List all clients for a site resource. list_site_resource_roles: GET /site-resource/{siteResourceId}/roles. List all roles for a site resource. list_site_resource_users: GET /site-resource/{siteResourceId}/users. List all users for a site resource. remove_private_resource_clients: POST /private-resource/{resourceId}/clients/remove. Remove a single client from a site resource. Clients with a userId cannot be removed. remove_private_resource_roles: POST /private-resource/{resourceId}/roles/remove. Remove a single role from a site resource. remove_private_resource_users: POST /private-resource/{resourceId}/users/remove. Remove a single user from a site resource. remove_public_resource_roles: POST /public-resource/{resourceId}/roles/remove. Remove a single role from a resource. remove_public_resource_users: POST /public-resource/{resourceId}/users/remove. Remove a single user from a resource. remove_public_resource_whitelist: POST /public-resource/{resourceId}/whitelist/remove. Remove a single email from the resource whitelist. remove_resource_ai_models: POST /resource/{resourceId}/ai-models/remove. Remove a single model from an inference resource allow/block list. Requires at least one attached AI provider. remove_resource_ai_providers: POST /resource/{resourceId}/ai-providers/remove. Remove an AI provider attachment from an inference resource. At least one provider must remain. remove_resource_roles: POST /resource/{resourceId}/roles/remove. Remove a single role from a resource. remove_resource_users: POST /resource/{resourceId}/users/remove. Remove a single user from a resource. remove_resource_whitelist: POST /resource/{resourceId}/whitelist/remove. Remove a single email from the resource whitelist. remove_site_resource_ai_models: POST /site-resource/{siteResourceId}/ai-models/remove. Remove a single model from an inference site resource allow/block list. Requires at least one attached AI provider. remove_site_resource_ai_providers: POST /site-resource/{siteResourceId}/ai-providers/remove. Remove an AI provider attachment from an inference site resource. At least one provider must remain. remove_site_resource_clients: POST /site-resource/{siteResourceId}/clients/remove. Remove a single client from a site resource. Clients with a userId cannot be removed. remove_site_resource_roles: POST /site-resource/{siteResourceId}/roles/remove. Remove a single role from a site resource. remove_site_resource_users: POST /site-resource/{siteResourceId}/users/remove. Remove a single user from a site resource. set_public_resource_header_auth: POST /public-resource/{resourceId}/header-auth. Set or update the header authentication for a resource. If user and password is not provided, it will remove the header authentication. set_public_resource_password: POST /public-resource/{resourceId}/password. Set the password for a resource. Setting the password to null will remove it. set_public_resource_pincode: POST /public-resource/{resourceId}/pincode. Set the PIN code for a resource. Setting the PIN code to null will remove it. set_resource_header_auth: POST /resource/{resourceId}/header-auth. Set or update the header authentication for a resource. If user and password is not provided, it will remove the header authentication. set_resource_password: POST /resource/{resourceId}/password. Set the password for a resource. Setting the password to null will remove it. set_resource_pincode: POST /resource/{resourceId}/pincode. Set the PIN code for a resource. Setting the PIN code to null will remove it. update_private_resource: POST /private-resource/{siteResourceId}. Update a site resource. update_private_resource_clients: POST /private-resource/{resourceId}/clients. Set clients for a site resource. This will replace all existing clients. Clients with a userId cannot be added. update_private_resource_roles: POST /private-resource/{resourceId}/roles. Set roles for a site resource. This will replace all existing roles. update_private_resource_users: POST /private-resource/{resourceId}/users. Set users for a site resource. This will replace all existing users. update_public_resource: POST /public-resource/{resourceId}. Update a resource. Policy fields (sso, mfa, pincode, password, whitelist) update the inline policy when no shared resource policy is assigned; when a shared policy is assigned those fields override the shared policy for this resource only. update_public_resource_roles: POST /public-resource/{resourceId}/roles. Set roles for a resource. This will replace all existing roles. When the resource has an inline policy defined (no shared resource policy assigned), roles are set on the inline policy instead of directly on the resource. update_public_resource_rule: POST /public-resource/{resourceId}/rule/{ruleId}. Update a resource rule. update_public_resource_users: POST /public-resource/{resourceId}/users. Set users for a resource. This will replace all existing users. When the resource has an inline policy defined (no shared resource policy assigned), users are set on the inline policy instead of directly on the resource. update_public_resource_whitelist: POST /public-resource/{resourceId}/whitelist. Set email whitelist for a resource. This will replace all existing emails. update_resource: POST /resource/{resourceId}. Update a resource. Policy fields (sso, mfa, pincode, password, whitelist) update the inline policy when no shared resource policy is assigned; when a shared policy is assigned those fields override the shared policy for this resource only. update_resource_ai_models: POST /resource/{resourceId}/ai-models. Replace the allow/block model selection for an inference resource. Requires at least one attached AI provider in select mode. Models must belong to a select-mode provider and their listType must match the provider catalog entry. An empty array clears the selection, which denies all models for select-mode providers. update_resource_ai_providers: POST /resource/{resourceId}/ai-providers. Replace the AI providers attached to an inference resource. Each provider uses accessMode inherit (default, uses the provider's own allow/block lists) or select (uses the resource's selected subset of that provider's catalog). An empty list clears all providers. Effective allow model keys must be unique across attached providers. update_resource_roles: POST /resource/{resourceId}/roles. Set roles for a resource. This will replace all existing roles. When the resource has an inline policy defined (no shared resource policy assigned), roles are set on the inline policy instead of directly on the resource. update_resource_rule: POST /resource/{resourceId}/rule/{ruleId}. Update a resource rule. update_resource_users: POST /resource/{resourceId}/users. Set users for a resource. This will replace all existing users. When the resource has an inline policy defined (no shared resource policy assigned), users are set on the inline policy instead of directly on the resource. update_resource_whitelist: POST /resource/{resourceId}/whitelist. Set email whitelist for a resource. This will replace all existing emails. update_site_resource: POST /site-resource/{siteResourceId}. Update a site resource. update_site_resource_ai_models: POST /site-resource/{siteResourceId}/ai-models. Replace the allow/block model selection for an inference site resource. Requires at least one attached AI provider in select mode. Models must belong to a select-mode provider and their listType must match the provider catalog entry. An empty array clears the selection, which denies all models for select-mode providers. update_site_resource_ai_providers: POST /site-resource/{siteResourceId}/ai-providers. Replace the AI providers attached to an inference site resource. Each provider uses accessMode inherit (default, uses the provider's own allow/block lists) or select (uses the site resource's selected subset of that provider's catalog). An empty list clears all providers. Effective allow model keys must be unique across attached providers. update_site_resource_clients: POST /site-resource/{siteResourceId}/clients. Set clients for a site resource. This will replace all existing clients. Clients with a userId cannot be added. update_site_resource_roles: POST /site-resource/{siteResourceId}/roles. Set roles for a site resource. This will replace all existing roles. update_site_resource_users: POST /site-resource/{siteResourceId}/users. Set users for a site resource. This will replace all existing users.

Inputs: action (required), body, query, params, +1 more.

pangolin_rolesA
DestructiveIdempotent

pangolin_roles covers the roles toolset (6 operations). Auth header Authorization Bearer. Self-hosted Pangolin CE only. Writes need confirm:true and PANGOLIN_ALLOW_WRITES=true. Omit confirm for a dry-run preview. Actions: add_role: POST /role/{roleId}/add/{userId}. Legacy: set exactly one role for the user (replaces any other roles the user has in the org). create_org_role: PUT /org/{orgId}/role. Create a role. delete_role: DELETE /role/{roleId}. Delete a role. get_role: GET /role/{roleId}. Get a role. list_org_roles: GET /org/{orgId}/roles. List roles. update_role: POST /role/{roleId}. Update a role.

Inputs: action (required), body, query, params, +1 more.

pangolin_sitesA
DestructiveIdempotent

pangolin_sites covers the sites toolset (11 operations). Auth header Authorization Bearer. Self-hosted Pangolin CE only. Writes need confirm:true and PANGOLIN_ALLOW_WRITES=true. Omit confirm for a dry-run preview. Actions: approve_site: POST /site/{siteId}/approve. Approve a pending site and approve (and enable when needed) its associated resources. create_org_site: PUT /org/{orgId}/site. Create a new site. delete_site: DELETE /site/{siteId}. Delete a site and all its associated data. get_org_pick_site_defaults: GET /org/{orgId}/pick-site-defaults. Return pre-requisite data for creating a site, such as the exit node, subnet, Newt credentials, etc. get_org_site: GET /org/{orgId}/site/{niceId}. Get a site by orgId and niceId. NiceId is a readable ID for the site and unique on a per org basis. get_site: GET /site/{siteId}. Get a site by siteId. list_org_sites: GET /org/{orgId}/sites. List all sites in an organization regenerate_re_key_site_secret: POST /re-key/{siteId}/regenerate-site-secret. Regenerate the credentials for a site. For newt sites a new secret is required; for wireguard sites a new public key is required. reject_site: POST /site/{siteId}/reject. Reject a pending site by deleting it and any associated resources that are still pending. restart_site: POST /site/{siteId}/restart. Restart a site. update_site: POST /site/{siteId}. Update a site.

Inputs: action (required), body, query, params, +1 more.

pangolin_targetsA
DestructiveIdempotent

pangolin_targets covers the targets toolset (3 operations). Auth header Authorization Bearer. Self-hosted Pangolin CE only. Writes need confirm:true and PANGOLIN_ALLOW_WRITES=true. Omit confirm for a dry-run preview. Actions: delete_target: DELETE /target/{targetId}. Delete a target. get_target: GET /target/{targetId}. Get a target. update_target: POST /target/{targetId}. Update a target.

Inputs: action (required), body, query, params, +1 more.

pangolin_usersA
DestructiveIdempotent

pangolin_users covers the users toolset (12 operations). Auth header Authorization Bearer. Self-hosted Pangolin CE only. Writes need confirm:true and PANGOLIN_ALLOW_WRITES=true. Omit confirm for a dry-run preview. Actions: create_org_user: PUT /org/{orgId}/user. Create an organization user. delete_org_invitations: DELETE /org/{orgId}/invitations/{inviteId}. Remove an open invitation from an organization delete_org_user: DELETE /org/{orgId}/user/{userId}. Remove a user from an organization. get_org_user: GET /org/{orgId}/user/{userId}. Get a user in an organization. get_org_user_by_username: GET /org/{orgId}/user-by-username. Get a user in an organization by username. When idpId is not passed, only internal users are searched (username is globally unique for them). For external (OIDC) users, pass idpId to search by username within that identity provider. get_user: GET /user/{userId}. Get a user by ID. list_org_invitations: GET /org/{orgId}/invitations. List invitations in an organization. list_org_users: GET /org/{orgId}/users. List users in an organization. list_users: GET /users. List non–server-admin users (server admin). update_org_create_invite: POST /org/{orgId}/create-invite. Invite a user to join an organization. update_user_2fa: POST /user/{userId}/2fa. Update a user's 2FA status. update_user_server_admin: POST /user/{userId}/server-admin. Promote or demote a user's server admin status (server admin).

Inputs: action (required), body, query, params, +1 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.9/5.0

    Scored across 6 tools

    Disambiguation3/5

    At the top level, the six tools split cleanly by domain (resources, sites, orgs, roles, targets, users), so an agent can usually pick the right tool. However, pangolin_resources is a 123-operation dispatcher containing near-identical parallel families (add_resource_users vs add_site_resource_users vs add_private_resource_users vs add_public_resource_users), and the private/public/site-resource variants are genuinely hard to distinguish without reading long descriptions.

    Naming Consistency4/5

    Tool names follow one clean pattern: pangolin_<plural domain>, which is easy to predict. Inside the action lists the verb_noun convention mostly holds, but there are outliers such as regenerate_re_key_site_secret, get_org_site_resource_nice, list_org_site_resources_org_id, and update_org_create_invite that break the pattern.

    Tool Count3/5

    Six tools is a reasonable surface count for a Pangolin connector, and grouping by domain avoids dozens of tiny tools. But each tool absorbs 3-123 operations, with pangolin_resources alone holding 123 actions, which pushes the effective selection burden far beyond what 6 tools suggests.

    Completeness4/5

    Coverage is broad: CRUD for resources, sites, orgs, roles, users, plus rules, targets, whitelist, access tokens, mTLS, AI providers/models, and site lifecycle (approve/reject/restart). Targets lack a create operation on their own toolset (created via the resource toolsets), which is a minor gap an agent can work around.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables AI agents and MCP clients to manage projects, merge requests, issues, pipelines, wiki, releases, tags, milestones, and more through stdio, SSE, or Streamable HTTP with PAT/OAuth authentication.
      226,557 npm
      MIT
    • F
      license
      Not graded
      quality
      B
      maintenance
      Serves sigit.si account, repository, issue, pull request, code-search, session, hook, and billing operations to AI agents over stdio, reusing the token stored by the CLI login and defaulting repository tools to the checkout the agent is pointed at. Tool lists can be trimmed with read-only mode or toolset selection, and a hosted HTTP endpoint offers the same tools.
      6
      -
    • A
      license
      C
      quality
      B
      maintenance
      Enables MCP clients to inspect and manage Semaphore UI automation through its management API, covering projects, templates, tasks, logs, inventories, repositories, and related configuration. It works over stdio or Streamable HTTP with schema-validated tools, read-only mode, project allowlists, and a bounded task-wait helper.
      213
      MIT
    • A
      license
      B
      quality
      B
      maintenance
      Enables assistants to read and modify contacts, conversations, messages, pipelines, tasks, inboxes, and AI agents through the CRM REST API, using separate read-only or read-write tool sets. Runs over local stdio or stateless Streamable HTTP with token-based scope separation.
      17
      MIT