paperclip-mcp
Allows creating a Paperclip project, optionally linked to a GitHub repository.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
paperclip-mcp
An MCP bridge to a Paperclip instance: its companies, its issues and whatever awaits a human decision, exposed to a remote MCP client (claude.ai, Claude Code, any compatible client).

A 48-second walkthrough is on the project page.
Why not the official MCP server
@paperclipai/mcp-server speaks stdio and exposes everything, approvals included,
plus free access to the API (paperclipApiRequest). This bridge exposes a closed
set of tools, each one subject to a policy.
Related MCP server: waylucid-agent-mcp
Policy per tool
policy.yaml gives each tool a mode:
Mode | Effect |
| the tool runs |
| the server asks for confirmation through MCP elicitation; a client that cannot ask is refused |
| the tool is not exposed (default for any tool missing from the file) |
Decision tools (issue_update, approval_decision, interaction_respond,
plan_confirm, action_request_decision, agent_resume, routine_run) only
accept ask or deny: otherwise the server refuses to start.
issue_update_without_confirmation in policy.yaml lists the issue_update
changes that run directly: assignment (assign: true) and the listed statuses.
Any other change asks for confirmation. Most clients cannot ask yet, so those
changes are refused there.
The Paperclip token is a board token, with every board right: this server is the only thing that restricts them.
Tools
Tool | Effect |
| companies, issue prefix, id |
| what awaits a human, across companies |
| issues, detail, comments, documents, pending cards |
| agents of a company |
| pending approvals and tool actions |
| comment on an issue |
| create an issue, always unassigned, optionally in a project |
| assign an issue (agent or |
| list a company's projects, create one (optional GitHub repository) |
| runs in progress across companies, an agent's last runs, a run's status, error and last agent messages |
| what happened on an issue: status changes, assignments, comments, runs |
| tokens and runs per agent over the last days (subscription runs cost 0 cents) |
| latest events of a company, its recurring routines |
| pause an agent (cancels its run in progress), wake it without a comment |
| clear an agent's error so it can run again |
| stop a run in progress |
| comment on an approval without deciding it |
| resume a paused agent, run a routine now; ask for confirmation |
| approve or reject an approval |
| answer a question card |
| accept or reject a plan |
| authorize or decline a suspended tool action |
In Paperclip, a comment only wakes the assigned agent, and an issue assigned to a
user wakes nobody. To make an agent act, issue_update assigns it, sets the status
to todo and adds a comment saying what to do.
Configuration
Variable | Role |
| default |
| dedicated board token |
| default |
| Cloudflare Access JWT validation, required |
| public hostname, otherwise the SDK answers 421 |
| local test without Cloudflare only |
Without CF_ACCESS_TEAM_DOMAIN and CF_ACCESS_AUD, the server refuses to start.
Run
docker build -t paperclip-mcp .
docker run -e PAPERCLIP_API_KEY=... -e CF_ACCESS_TEAM_DOMAIN=... -e CF_ACCESS_AUD=... \
-v ./policy.yaml:/app/policy.yaml:ro -p 9200:9200 paperclip-mcpThe MCP endpoint is /mcp, the health check /healthz.
License
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Work with roles, tasks and delegated agent work within current workspace permissions. Setup: In a remote MCP client that supports Streamable HTTP and OAuth, add https://platform.samuelz.com/api/v1/mcp/operator?toolset=agent. Sign in to Samuelz and select your authorized workspace. An active workspace membership and the relevant module permissions are required. Review the requested permissions before authorizing. Existing approval requirements continue to apply.
Toolstile is a managed MCP gateway that connects remote MCP servers behind one endpoint, with per-agent permissions, shared accounts and activity logs. Connect at https://mcp.toolstile.com/mcp over Streamable HTTP with OAuth; sign in at https://toolstile.com, select a workspace and connect your upstream servers. Available tools, resources and prompts depend on that workspace and the agent's granted access.
Host any HTTP API as MCP tools with a tamper-evident cross-agent settlement ledger.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceProvides a policy-controlled MCP gateway that lets agents invoke tools with explicit policies, bounded execution, scoped visibility, and decision receipts.MIT
- AlicenseNot gradedqualityBmaintenanceEnables role-gated management of ops desk contacts, cases, and tasks via MCP, with tool schemas and availability filtered per role to enforce permission boundaries, over stdio or Streamable HTTP.MIT
- AlicenseNot gradedqualityBmaintenanceExposes a remote coding agent as MCP tools so an MCP client can delegate tasks, manage their lifecycle, and inspect the agent card, with permission decisions enforced inside the bridge.1Apache 2.0
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients to search policies, look up bookings, list activities, create booking requests, issue or approve credits, and review audit records under role-based access. It enforces tenant isolation, filters fields by role, strips planted instructions from tool results, rate-limits each key, and writes tamper-evident audit logs.MIT