tunnel-mcp
Create, connect, list, and inspect MCP tunnel runtimes through the local tunnel-client plugin.
Skill by dylmarriner
Chalk Labs
Need help deploying tunnel-mcp?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/dylmarriner-tunnel-mcp
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/tunnel-mcp
What's inside
- Skill name
tunnel-mcp- Description
- Create, connect, list, and inspect MCP tunnel runtimes through the local tunnel-client plugin. Use when Codex needs to manage secure MCP tunnels with aliases and native tunnel-client runtime processes.
- License
- MIT
- Instructions
- 65 lines in SKILL.md · view on GitHub
Files (6)
- SKILL.md
- binary.md · references/
- profiles-state-and-keys.md · references/
- runtime-flows.md · references/
- setup-and-install.md · references/
- troubleshooting.md · references/
SKILL.md (first lines)
# Tunnel MCP Use `scripts/tunnel_mcp` from this plugin when a user asks Codex to manage MCP tunnels through `tunnel-client`. The plugin entrypoint is a thin router onto the public native `tunnel-client runtimes ...` and `tunnel-client admin-profiles ...` command trees. When the `tunnel-mcp` MCP app tools are available, use them first instead of manual shell routing: - `install_or_select_tunnel_client` - `create_tunnel_runtime` - `connect_stdio_mcp` - `list_runtime_aliases` - `runtime_status` - `stop_runtime` The app tools are an operator surface over native `tunnel-client`; they orchestrate `tunnel-client runtimes ...`, normalize structured output, and keep tunnel protocol/runtime behavior in the Go binary. Before acting, consult only the smallest relevant reference under `references/`: - `references/binary.md`: how to find or obtain a public-safe `tunnel-client` binary - `references/setup-and-install.md`: install, export, reset, binary-vs-bundle setup - `references/profiles-state-and-keys.md`: profiles, state dirs, admin/runtime key split - `references/runtime-flows.md`: create, connect, list, status, stop, rm, attach by tunnel id - `references/troubleshooting.md`: `/healthz`, `/readyz`, `/ui`, status, logs, stale aliases ## Rules - Use `tunnel-client admin tunnels` for remote tunnel CRUD. Do not call raw tunnel-service HTTP endpoints from this plugin. - Route operational actions through `tunnel-client runtimes ...` and `tunnel-client admin-profiles ...`. - Use `scripts/tunnel_mcp self-check` for plugin/binary/router compatibility; it must report secret reference presence without printing secret values. - Use native `tunnel-client run --profile <name>` only when the user intentionally wants a foreground daemon attached to the current terminal; do not translate profile files into flags in the plugin layer. - For a long-lived local runtime managed by Codex, use `tunnel-client runtimes connect ...`; do not use `nohup` or `disown` as the tunnel-client supervision path. - After `runtimes connect`, run `tunnel-client runtimes status <alias>` before reporting success. Only report success when status shows the managed runtime running with health reported; use `--json` when Codex needs explicit `process_running`, `healthy`, and `ready` fields. - Do not assume a source checkout, build system, helper, or tmux. The installed plugin must work with the selected `tunnel-client` binary alone. - Treat ambient `PATH` binary candidates as diagnostics unless selected through `--tunnel-client-bin`, `TUNNEL_CLIENT_BIN`, or `.tunnel-client-bin`. - Tunnel state, admin profiles, generated runtime profiles, stale-alias handling, cleanup classification, and local process management are owned by native `tunnel-client`; consult the relevant reference before explaining those details. - Keep admin and runtime credentials split: admin CRUD uses `admin-profiles`; runtime attach/connect uses `--runtime-api-key env:NAME` or `file:/path`. Do not pass literal keys. - Never write literal API keys, bearer tokens, cookies, or inline `sk-` style secret material into plugin state or generated configs. - Surface `control_plane_poll_health` separately from `/healthz` and `/readyz`; local readiness can be green while control-plane polling fails through a dead proxy.
From dylmarriner/scos-memory, MIT.
More from dylmarriner/scos-memory
- 0.524score
scos-memory
dylmarriner
Use the SCOS Memory Fabric's mcp-gateway tools (scos_recall, scos_status, scos_explain, scos_user_model, scos_memory_graph, scos_correct, scos_forget) to…
SkillBFreshness: BClaude Code +9 - 0.524score
scos-memory
dylmarriner
Use the SCOS Memory Fabric's mcp-gateway tools (scos_recall, scos_status, scos_explain, scos_user_model, scos_memory_graph, scos_correct, scos_forget…
SkillBFreshness: BClaude Code +9 - 0.521score
hostile-concurrency-auditor
dylmarriner
Find races, TOCTOU, stale reads, locking gaps, optimistic concurrency failures, duplicate jobs/events, retries, ordering, idempotency, cancellation races, and…
SkillBFreshness: BClaude Code +9 - 0.521score
hostile-data-flow-auditor
dylmarriner
Trace attacker-influenced data through parsing, normalization, validation, storage/reload, transformation, serialization, caches, templates, filesystem…
SkillBFreshness: BClaude Code +9 - 0.521score
hostile-authorization-auditor
dylmarriner
Map every sensitive operation to every reachable interface and verify ownership, roles, object/function auth, tenant isolation, admin, service, worker, and…
SkillBFreshness: BClaude Code +9 - 0.521score
hostile-business-logic-abuse-auditor
dylmarriner
Attack product invariants using legitimate functionality: sequence abuse, replay, duplicates, quotas, entitlements, approvals, ownership, lifecycle…
SkillBFreshness: BClaude Code +9 - 0.521score
hostile-blind-spot-auditor
dylmarriner
Run last and explicitly try to prove the other auditors missed something, prioritizing clean, internal-only, operational, configuration-only, well-tested, and…
SkillBFreshness: BClaude Code +9 - 0.521score
hostile-control-flow-auditor
dylmarriner
Trace sensitive operations from every reachable entry through callers, callees, callbacks, middleware, RPC, events, workers, queues, persistence, external…
SkillBFreshness: BClaude Code +9 - 0.521score
hostile-configuration-auditor
dylmarriner
Audit environment variables, defaults, flags, permissions, dev/prod differences, debug, deployment, containers, infrastructure, unsafe combinations, and…
SkillBFreshness: BClaude Code +9 - 0.521score
hostile-authentication-identity-auditor
dylmarriner
Audit identity lifecycle, sessions, cookies, tokens, verification, refresh, revocation, MFA, recovery, impersonation, linking, OAuth/OIDC, API keys, service…
SkillBFreshness: BClaude Code +9 - 0.520score
scos-memory
dylmarriner
Use the SCOS Memory Fabric tools (scos_recall, scos_status, scos_explain, scos_user_model, scos_memory_graph, scos_correct, scos_forget, scos_graphify_query…
SkillBFreshness: BClaude Code +9 - 0.513score
scos-memory
dylmarriner
Use SCOS Memory Fabric for prior context and governed memory operations.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 1, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/dylmarriner/scos-memory
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from dylmarriner
- 0.524score
scos-memory
dylmarriner
Use the SCOS Memory Fabric's mcp-gateway tools (scos_recall, scos_status, scos_explain, scos_user_model, scos_memory_graph, scos_correct, scos_forget) to…
SkillBFreshness: BClaude Code +9 - 0.524score
scos-memory
dylmarriner
Use the SCOS Memory Fabric's mcp-gateway tools (scos_recall, scos_status, scos_explain, scos_user_model, scos_memory_graph, scos_correct, scos_forget…
SkillBFreshness: BClaude Code +9 - 0.521score
hostile-authorization-auditor
dylmarriner
Map every sensitive operation to every reachable interface and verify ownership, roles, object/function auth, tenant isolation, admin, service, worker, and…
SkillBFreshness: BClaude Code +9 - 0.521score
hostile-authentication-identity-auditor
dylmarriner
Audit identity lifecycle, sessions, cookies, tokens, verification, refresh, revocation, MFA, recovery, impersonation, linking, OAuth/OIDC, API keys, service…
SkillBFreshness: BClaude Code +9 - 0.521score
hostile-blind-spot-auditor
dylmarriner
Run last and explicitly try to prove the other auditors missed something, prioritizing clean, internal-only, operational, configuration-only, well-tested, and…
SkillBFreshness: BClaude Code +9 - 0.521score
hostile-business-logic-abuse-auditor
dylmarriner
Attack product invariants using legitimate functionality: sequence abuse, replay, duplicates, quotas, entitlements, approvals, ownership, lifecycle…
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get tunnel-mcp running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
tunnel-mcp skill. Agent Mart. https://agentmart.dev/skills/dylmarriner-tunnel-mcp (last updated 2026-10-24)