Pushary MCP server
Commit Nov 15, 2026Enables AI agents to send push notifications and request human approvals or answers via mobile, Mac, or Slack.
Also known as Pushary/pushary-skill, pushary-skill
- Stars
- 1
- Tools
- 6
- Downloads, 30 days
- —
- Latest version
- 1.5.2
- Last commit
- Nov 15, 2026
- License
- MIT
What is Pushary MCP?
Pushary enables AI agents to send push notifications and request human approvals or answers via mobile, Mac, or Slack. It exposes 6 tools, such as send_notification, ask_user, wait_for_answer.
Summary generated from the project's README
About Pushary MCP server
Pushary provides a human-in-the-loop mechanism for AI agents by connecting them to push notifications. This allows developers and teams to receive task updates or respond to agent queries via mobile devices, Mac apps, Slack, or web browsers. The server enables three specific interaction types: yes/no confirmations, multiple-choice selections, and free text input. It is designed for users of coding agents and frameworks like LangGraph, Vercel AI SDK, and Hermes.
To use the service, developers can perform a local setup using npx pushary@latest setup to pair their agent with a phone. While manual MCP configuration is possible using a Bearer token and a specific API URL, hosted delivery and personal accounts require a paid Pushary plan. The system supports different delivery modes such as push_first, push_only, notify_only, and terminal_only to control how and when notifications reach the user.
What you can do with it
- 1Approve risky terminal commandsA developer can route dangerous shell commands to a mobile device for quick authorization.
- 2Manage multi-agent workflowsUsers can identify which specific agent is requesting information when running several processes at once.
- 3Delegate approvals to team leadsAn organization can set up routing rules to ensure specific tool patterns are reviewed by an administrator.
- 4Provide context-rich feedbackAn AI agent can send detailed information like error logs or file changes to a user's phone for review.
Written from the project's README. Every use case is checked against a quote from it.
How to install Pushary MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Pushary MCP in Claude Code
$ claude mcp add --transport http pushary-skill https://pushary.com/api/mcp/mcpInstall Pushary MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"pushary-skill": {
"url": "https://pushary.com/api/mcp/mcp"
}
}
}Install Pushary MCP in VS Code
.vscode/mcp.json
{
"servers": {
"pushary-skill": {
"type": "http",
"url": "https://pushary.com/api/mcp/mcp"
}
}
}Install Pushary MCP in VS Code CLI
$ code --add-mcp '{"name":"pushary-skill","type":"http","url":"https://pushary.com/api/mcp/mcp"}'Install Pushary MCP in Codex
$ codex mcp add pushary-skill --url https://pushary.com/api/mcp/mcpInstall Pushary MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.pushary-skill] url = "https://pushary.com/api/mcp/mcp"
Install Pushary MCP in Gemini CLI
$ gemini mcp add -s user --transport http pushary-skill https://pushary.com/api/mcp/mcpInstall Pushary MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"pushary-skill": {
"url": "https://pushary.com/api/mcp/mcp",
"type": "http"
}
}
}Pushary MCP tools 6
Detected from the READMEsend_notificationask_userwait_for_answercancel_questionlist_sessionspropose_scope
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablepushary/pushary-skill is public and reachablegithub.com/pushary/pushary-skill ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-11-07github.com/pushary/pushary-skill ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model6 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeinitialize answered with protocol 2025-06-18 in 108 msPass
README
View on GitHubStart here
Try an approval without signing up → connect an open phone page → approve or decline → see the agent continue or stop. This browser demo uses polling and temporary state, not real push delivery or the production ledger.
| What you want to build | Start with |
|---|---|
| Notifications and questions for a coding agent | The setup instructions below |
| An enforced tool approval in the Vercel AI SDK | Runnable AI SDK example |
| A LangGraph workflow that branches on a human decision | Runnable LangGraph example |
| Another agent framework | All Pushary integrations |
| When an agent should stop and ask a person, and how to add that step in any framework | The pushary-human-in-the-loop skill |
The skill and adapters are MIT-licensed. Hosted phone delivery requires a Pushary account; embedding approvals for your own users requires Partner access. The two framework examples also run locally with simulated answers and no credentials.
If Pushary helped you, star this repo. Want to help? Public issues and patches are welcome.
Pushary lets your coding agent send task updates and ask you for a decision on your phone. Supported host hooks also enforce approvals before an action runs.
Hosted delivery requires a paid Pushary plan. MCP questions and notifications work with any compatible client; enforced approvals depend on the host integration.
How It Works
AI Agent -> MCP Protocol -> Pushary API -> Push Notification -> Your Phone
Pushary is an MCP server that connects your AI coding agent to push notifications. The agent calls Pushary's tools over the Model Context Protocol, and you receive notifications instantly on any device.
Three question types - yes/no confirmations, multiple choice, and free text input. Your agent picks the right one for the situation.
Rich context notifications - agents can include file changes, error details, and suggested next steps in a detail page you see when tapping the notification.
Agent identification - when you run multiple agents, each notification shows which agent is asking so you always know what you're responding to.
Permission hooks - route Claude Code's tool approval prompts through push notifications so you can approve or deny from your phone.
Personal setup: phone first
Run the pairing setup in your agent's terminal:
npx pushary@latest setup
Install Pushary on your phone, scan the QR or open the printed link, compare the fingerprints, and approve. Setup then configures the selected agent's tools, supported hooks and skill. You do not need to copy an API key first. Personal accounts require a paid plan. Existing credentials are reused.
Verify setup:
npx pushary@latest doctor
Ask your agent for one harmless test question. Confirm the intended device receives it and the answer returns to the same task.
For Hermes specifically:
npx pushary@latest setup --agents hermes
This writes the native plugin to ~/.hermes/plugins/pushary and turns it on with hermes plugins enable pushary and hermes config set. Restart Hermes afterward with hermes gateway restart. The plugin provides notification, question, wait, cancel, reminder and scope tools, plus Partner enrollment and customer-question tools. Its parameters use snake_case; use the Hermes skill, not MCP parameter names. The native approval transport preserves Hermes' session and standing approvals.
Mac notch and other answer surfaces
Install Pushary for Mac, sign in with the same personal account and connect your agents from the app. The notch provides confirm, choice, text and question-set controls with keyboard support. Keep the app running for presence and delivery; verify one harmless question there, then phone fallback while away from the Mac.
| Surface | Answers |
|---|---|
| Mobile | Confirm, choice and text in the app. Supported confirm notifications expose lock-screen approve/deny; arbitrary choices and text open the app. |
| Mac notch | Questions for the signed-in account, including keyboard answering, and Partner customers' questions once they connect the Mac from their phone. |
| Slack | Buttons, choice menus and text modals when the integration and recipient are configured. |
| Browser | Decision-page fallback and browser notifications when permission is enabled. |
Delivery follows your settings and presence. push_first uses presence, push_only requests push every time, notify_only keeps decisions in the current client, and terminal_only avoids push. A successful API call alone does not prove a device displayed the request.
Team setup: send a risky step to a lead
On Pushary for Teams, each person runs the same setup and connects their own agents. Their agents' questions go to them. An owner or admin can send a chosen step to someone else with a routing rule in Policies, under Approval routing:
| Field | Example |
|---|---|
| Tool pattern | Bash(git push:*) |
| Repository | infra, or all repositories |
| Route to | The Admins role, or one person |
Claude Code, Codex, Cursor and Gemini CLI shell calls all match a Bash(...) rule, so one rule covers a team that runs several agents. Whoever answers in the phone app, Mac app or dashboard is recorded by name, next to whose agent asked.
What a routing rule doesn't do:
- It doesn't lock the terminal. If nobody answers in time, the person running the agent can still approve at the agent's own prompt, and that yes isn't recorded.
- The phone can only deny risky steps such as a force push or
rm -r. Approve those in the dashboard. - It needs a second person. Routing starts once someone else joins the workspace.
Team is $59 a month for 5 people, plus $12 for each extra person. How a routing rule works, step by step.
Partner setup: your own customers
Personal pairing connects you, the operator. Partner integrations enroll each of your application's customers through a scoped connection link and address decisions using your stable customer ID. Customers use the mobile enrollment flow; do not route their approvals to your personal Mac inbox or share an operator API key.
Start with the Partner integration guide, then a Mastra agent example, AI SDK example or LangGraph example. Tools choose confirm, choice or text. Approving an action and supplying an answer are different operations; a text answer saying “yes” is not permission to execute another tool.
Manual fallback
For a client that needs manual MCP configuration, obtain your key in the Pushary dashboard and configure:
{
"mcpServers": {
"pushary": {
"url": "https://pushary.com/api/mcp/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}
Keep the key private. Install the skill with npx skills add Pushary/pushary-skill if the client supports skills.sh. Manual MCP provides cooperative questions and notifications; enforced approvals require the supported host hooks/runtime integration.
Claude Code users can alternatively install this repository as a plugin:
/plugin marketplace add Pushary/pushary-skill
/plugin install pushary
That path reads PUSHARY_API_KEY from the environment. Pick one installation path: installing the plugin on top of CLI-installed Claude hooks can run hooks twice. Use npx pushary@latest clean before switching paths.
The plugin starts each hook through npx, which is too slow for the hook that streams live reply previews to your phone, so the plugin leaves that hook out. For live previews, install with npx pushary@latest setup instead. Setup installs every hook as a local command.
Setup: Lovable
Lovable is a hosted app builder, so there is no local install step (npx skills add does not apply). You connect the MCP server in Lovable's UI, then paste the skill into Lovable's Knowledge so the agent uses it on its own.
1. Connect the MCP server. In Lovable, go to Settings -> Connectors -> Personal connectors (paid Lovable plans), click New MCP server, set the URL to https://pushary.com/api/mcp/mcp, choose Bearer token, and paste your API key (pk_xxx.xxx).
2. Add the skill to Knowledge. Lovable cannot install skills via npx, so paste the skill guidance into Settings -> Knowledge. Use the condensed SKILL-LITE.md as the source. This makes the Lovable agent notify you when a build finishes and ask before risky changes, without you prompting each time.
Lovable gets notifications and questions only (no enforced gate, since it has no permission hook). Full walkthrough: Lovable guide.
Setup: Claude Chat and Cowork
For Claude Chat or Claude Code, use Pushary for Claude. In Chat, open Customize > Plugins > Add > Add marketplace, add https://github.com/Pushary/claude-plugin, and install Pushary for Claude. In Claude Code, run /plugin marketplace add Pushary/claude-plugin, then /plugin install pushary@pushary-claude-plugin.
For Cowork, the existing Pushary for Cowork plugin remains available. Add https://github.com/Pushary/cowork-plugin as the marketplace and install Pushary for Cowork. Cowork also supports standing instructions under Settings > Cowork. Its existing plugin, marketplace, and pushary-cowork skill identifiers are preserved.
Both bundles use the public OAuth connector and the same shared skill. Connect Pushary from the plugin's Connectors tab in Chat or Cowork, or /mcp in Claude Code, and sign in with the same Pushary account used by your phone or Mac. No CLI or API key is needed for either bundle.
If the connector is missing, add https://pushary.com/api/mcp/mcp under Customize > Connectors > Add custom connector and leave the OAuth Client ID and Secret fields empty. Enable Pushary in the conversation, ask one harmless test question, and verify your answer returns to Claude.
These bundles provide questions and notifications and install no native permission hooks. For Claude Code approval hooks, use the Claude Code setup above. Choose one installation path per app to avoid duplicate Pushary connectors. Full Claude guide.
Tools
The skill guides these MCP tools:
| Tool | Description |
|---|---|
send_notification |
Send a push notification with optional rich context (file changes, errors, next steps) |
ask_user |
Ask the user a question via push - yes/no, multiple choice, or free text |
wait_for_answer |
Long-poll for the user's response to a question |
cancel_question |
Cancel a pending question that's no longer relevant |
list_sessions |
Read-only view of your live agent sessions and pending questions |
propose_scope |
Ratify the boundary of a run: file globs, enforced on supported hosts, or a recorded promise when the run changes no files |
Full tool documentation with parameters, examples, and usage guidelines is in skills/pushary/SKILL.md.
Human-in-the-Loop
The agent can ask you decisions via push and wait for your answer:
Agent: "Which auth strategy should I use?"
Options: JWT tokens / Session cookies / OAuth2 + PKCE
-> push to your phone
You: tap "JWT tokens"
Agent: proceeds with JWT implementation
Supports three question types:
- Confirm - yes/no binary decisions
- Select - pick from 2-6 options
- Input - free text response
Read answered, status and handoffAction (or nextAction) from the tool result. Poll only as directed; cancel a live question before handing it to another surface and honor any winning answer. Expiry and waits follow server policy. Silence is not approval, and a late reply cannot restart an ended agent turn.
Packages
| Package | Registry | Description |
|---|---|---|
pushary |
npm | The Pushary CLI: setup, permission hooks and doctor. Also published as @pushary/agent-hooks, the same package |
hermes-plugin-pushary |
PyPI | Hermes Agent native plugin |
Compatible Agents
Works with any agent that supports skills.sh or the Model Context Protocol:
- Claude Code (MCP + permission hooks)
- Claude Cowork (custom connector + skill upload)
- Hermes Agent (native plugin or MCP)
- Cursor (MCP)
- Windsurf (MCP)
- Lovable (MCP connector + skill via Knowledge)
- OpenAI Codex (MCP)
- Other clients that support remote MCP servers
Publishing the MCP registry entry
server.json is not published by merging it. The MCP registry serves one record per version, so an edit here reaches nobody until the new version is pushed to the registry, and the old text keeps being what every agent reads.
Everyday path: bump version in server.json, merge to main, then sync the public skill mirror. Its release workflow publishes the new registry entry.
The release workflow publishes from the public Pushary repository so GitHub OIDC can prove ownership of the io.github.Pushary/pushary namespace. Verify the workflow and registry result after release.
Manual fallback, from this directory:
curl -L "https://github.com/modelcontextprotocol/registry/releases/latest/download/mcp-publisher_$(uname -s | tr '[:upper:]' '[:lower:]')_$(uname -m | sed 's/x86_64/amd64/;s/aarch64/arm64/').tar.gz" | tar xz mcp-publisher
./mcp-publisher login github
./mcp-publisher publish
Check what the registry actually serves, which is the only number that matters:
curl -s "https://registry.modelcontextprotocol.io/v0/servers?search=pushary"
That endpoint returns every version, oldest first. Read the entry whose _meta."io.modelcontextprotocol.registry/official".isLatest is true; the first row in the list is the oldest record, not the live one.
Contributing
Contributions are welcome! Please read the contributing guide before submitting a pull request.
Security
If you discover a security vulnerability, please report it responsibly. See SECURITY.md for details.
Funding
This project is fully funded by RalphNex OU, an Estonian software development agency.
License
MIT - Copyright (c) 2025 RalphNex OU
Pushary MCP questions
How do I add Pushary MCP to Claude Code?
Run claude mcp add --transport http pushary-skill https://pushary.com/api/mcp/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Pushary MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Pushary MCP provide?
It exposes 6 tools, including send_notification, ask_user, wait_for_answer, cancel_question, list_sessions.
What kind of questions can the AI agent ask?
The agent can ask three types of questions: yes/no confirmations, multiple choice, and free text input.
How can I approve or deny actions from my phone?
You can install the Pushary app on your phone to receive notifications and respond to agent requests directly.
Does Pushary work with Claude Code?
Yes, you can route Claude Code's tool approval prompts through push notifications or install it as a plugin.
Can I use Pushary with my own users in an application?
Yes, you can use Partner access to embed approvals for your own users using a scoped connection link.