Deploy BankMCP™ to a small server so it works in claude.ai and on the phone: Railway or Fly.io, volume, domain, setup page, connector.
$ npx skills add noskillish/bankmcp --skill deploy -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install noskillish/bankmcp deploy --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/noskillish/bankmcp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugin/skills/deploy .claude/skills/deploy && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "deploy" agent skill from https://github.com/noskillish/bankmcp/tree/main/plugin/skills/deploy into .claude/skills/deploy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deploy", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/noskillish/bankmcp/tree/main/plugin/skills/deployType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add noskillish/bankmcp --skill deploy -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install noskillish/bankmcp deploy --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/noskillish/bankmcp.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugin/skills/deploy .agents/skills/deploy && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "deploy" agent skill from https://github.com/noskillish/bankmcp/tree/main/plugin/skills/deploy into .agents/skills/deploy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deploy", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add noskillish/bankmcp --skill deploy -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install noskillish/bankmcp deploy --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/noskillish/bankmcp.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugin/skills/deploy .cursor/skills/deploy && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "deploy" agent skill from https://github.com/noskillish/bankmcp/tree/main/plugin/skills/deploy into .cursor/skills/deploy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deploy", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/noskillish/bankmcp.git --path plugin/skills/deploy--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add noskillish/bankmcp --skill deploy -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install noskillish/bankmcp deploy --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/noskillish/bankmcp.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugin/skills/deploy .gemini/skills/deploy && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "deploy" agent skill from https://github.com/noskillish/bankmcp/tree/main/plugin/skills/deploy into .gemini/skills/deploy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deploy", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install noskillish/bankmcp deployInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add noskillish/bankmcp --skill deploy -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/noskillish/bankmcp.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugin/skills/deploy .github/skills/deploy && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "deploy" agent skill from https://github.com/noskillish/bankmcp/tree/main/plugin/skills/deploy into .github/skills/deploy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deploy", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add noskillish/bankmcp --skill deploy -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install noskillish/bankmcp deploy --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/noskillish/bankmcp.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugin/skills/deploy .opencode/skills/deploy && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "deploy" agent skill from https://github.com/noskillish/bankmcp/tree/main/plugin/skills/deploy into .opencode/skills/deploy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "deploy", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
deployDeploy BankMCP™ to a small server so it works in claude.ai and on the phone: Railway or Fly.io, volume, domain, setup page, connector.
Deploy is an agent skill from noskillish/bankmcp. Deploy BankMCP™ to a small server so it works in claude.ai and on the phone: Railway or Fly.io, volume, domain, setup page, connector. Use when the user says "deploy bankmcp", "host it", "/deploy", "use it on my phone", or "add it to claude.ai".
Its SKILL.md is about 740 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in DevOps & Cloud, covering Deployment and LLM inference and serving. It works with Model Context Protocol, Docker, Ollama and OpenAI. The repository describes itself as: BankMCP™: your AI can now read your bank. Self-hosted, read-only MCP server for your own bank accounts via open banking (Enable Banking). Standard MCP; tested with Claude and… The licence is MIT.
6 steps, taken from the step headings in SKILL.md.
Read from SKILL.md and the folder at commit f28fac6. It shows what the files ask for, not the result of running them.
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Shell commands in SKILL.md call:
railwayflydockerclaudeFrom the folder's file list and the shell code blocks in SKILL.md.
Links to these hosts (documentation or services it may open):
railway.comFrom URLs in SKILL.md, links to its own repository left out.
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Deploy loads about 744 tokens when it runs. Until then it costs about 63 tokens; SKILL.md has 386 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
The full file from noskillish/bankmcp at commit f28fac6, republished under its MIT licence (© noskillish). 386 words, ~744 tokens.
.claude/skills/deploy/SKILL.md (or your agent's skills folder).Guide one person through a hosted deployment. Prefer Railway unless the user names another host. Run what you can with the CLI; the user does the dashboard clicks, their bank login and their claude.ai settings.
Ask which they have: Railway, Fly.io, Render, or their own box with Docker. If none, recommend Railway (https://railway.com) and wait until they have an account.
If the railway CLI is installed and logged in (railway whoami), do it from the terminal:
railway init
railway add --service bankmcp --repo noskillish/bankmcp --branch main
railway volume add -m /data
railway domain --port 8080Otherwise, in the Railway dashboard: New Project, Deploy from GitHub repo noskillish/bankmcp; add a Volume mounted at /data; Settings, Networking, Generate Domain on port 8080.
Report the public address. No variables are needed; the server detects its own address on Railway.
Fly: from a clone of the repo, fly launch --copy-config --no-deploy (the repo's fly.toml already mounts /data and checks /healthz), fly volumes create data --size 1, fly deploy. Render: the Deploy to Render button in the README uses render.yaml; a persistent disk needs a paid instance. Docker: docker run -d --name bankmcp --restart unless-stopped -p 8080:8080 -v bankmcp-data:/data ghcr.io/noskillish/bankmcp:latest (or docker compose up -d from a clone), then a TLS proxy in front and BASE_URL set to the public https address.
Tell the user to open the public address. It shows a setup page with the values for Enable Banking's form. Walk them through registering the application as in the setup skill (environment, redirect URL, description, privacy and terms URLs, key download), then entering the application id, the .pem file and a password of twelve characters or more. The status page then shows the connector URL.
claude.ai (personal Pro or Max account): Settings, Connectors, Add custom connector, name BankMCP™, URL https://<address>/mcp, leave OAuth fields empty, Add, Connect, enter the password.
Team or Enterprise workspaces only allow Owners to add custom connectors; say so if the button is missing.
Claude Code: claude mcp add --transport http bankmcp https://<address>/mcp, then /mcp to sign in.
In the connected client: "connect my bank". Same flow as locally; the redirect returns to the server's /callback.
NOTIFY_WEBHOOK_URL to a Slack incoming webhook for sign-in alerts and watch notifications.© noskillish, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Just SKILL.md in plugin/skills/deploy of noskillish/bankmcp.
Open the folder on GitHubat commit f28fac6
Deploy next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Deploy this skillnoskillish/bankmcp | 276 | — | ~744 | Automated safety check: Pass | MIT | |
| Chatqna Docker Deployopen-edge-platform/edge-ai-libraries | 168 | — | ~2.9k | Automated safety check: Pass | Apache-2.0 | |
| Chatqna Troubleshootopen-edge-platform/edge-ai-libraries | 168 | — | ~2.6k | Automated safety check: Pass | Apache-2.0 | |
| vLLM Model ServingOrchestra-Research/AI-Research-SKILLs | 13k | 6 repos | ~2.3k | Automated safety check: Pass | MIT | |
| Cognee Docker Setuptopoteretes/cognee | 32k | 1 repos | ~901 | Automated safety check: Notes | Apache-2.0 | |
| Perfupraullenchai/Rapid-MLX | 3.9k | — | ~1.6k | Automated safety check: Notes | Custom licence |
open-edge-platform/edge-ai-libraries
Deploy Chat Question-and-Answer Core with Docker Compose (OpenVINO CPU, OpenVINO GPU, or Ollama CPU), including env setup, profile selection, startup verification, health checks, and teardown.
open-edge-platform/edge-ai-libraries
Troubleshoot Chat Question-and-Answer Core end-to-end across Docker Compose and Helm deployments, including startup failures, health/API errors, runtime mismatches (OpenVINO vs Ollama), model/config…
Orchestra-Research/AI-Research-SKILLs
Deploys LLMs with vLLM for high-throughput serving, covering the OpenAI-compatible server, offline batch inference, monitoring and a Docker rollout.
topoteretes/cognee
Runs the Cognee AI memory platform in Docker, from a one-file prebuilt image to a full compose stack with UI, MCP server, Postgres and Neo4j.
raullenchai/Rapid-MLX
Autonomous performance optimization: research, PoC, benchmark, implement, review, PR
eat-pray-ai/yutu
A skill your agent uses whenever the user mentions YouTube, video uploads, channel management, playlists, video SEO, or any YouTube Data API operation.
noskillish/bankmcp
Answer questions about the user's own bank accounts and money using the bank MCP tools (listaccounts, getbalances, gettransactions, watches).
noskillish/bankmcp
Set up BankMCP™ on this machine step by step: check Node, register the local MCP server, walk through the Enable Banking application, finish the setup page and connect the first bank.
Works with
Categories
Deploy BankMCP™ to a small server so it works in claude.ai and on the phone: Railway or Fly.io, volume, domain, setup page, connector. Deploy is an agent skill from noskillish/bankmcp.io, volume, domain, setup page, connector.
Deploy fits situations like: the user says deploy bankmcp; use it on my phone; add it to claude.ai.
Run `npx skills add noskillish/bankmcp --skill deploy -a claude-code`. Or copy the skill folder (plugin/skills/deploy in noskillish/bankmcp) into .claude/skills/deploy in your project. Claude Code loads it when a task matches its description.
Run `npx skills add noskillish/bankmcp --skill deploy -a codex`. Or copy the skill folder (plugin/skills/deploy in noskillish/bankmcp) into .agents/skills/deploy in your project. Codex loads it when a task matches its description.
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add noskillish/bankmcp --skill deploy -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deploy, .gemini/skills/deploy, .github/skills/deploy and .opencode/skills/deploy in your project.
Going by SKILL.md and its folder, Deploy needs the command-line tools its instructions call (railway, fly, docker and claude). Our summary lists: Docker.
SKILL.md names 1 domain. As links in the text: railway.com. This is read from the text; nothing was executed.
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
Deploy is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
About 744 tokens (SKILL.md is roughly 3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
Skills that share tags, products or a category with Deploy: Chatqna Docker Deploy (open-edge-platform/edge-ai-libraries, 168 stars), Chatqna Troubleshoot (open-edge-platform/edge-ai-libraries, 168 stars), vLLM Model Serving (Orchestra-Research/AI-Research-SKILLs, 13k stars) and Cognee Docker Setup (topoteretes/cognee, 32k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
noskillish (a GitHub user) maintains it in noskillish/bankmcp, which has 276 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on September 28, 2026.
Source: noskillish/bankmcp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.
