Add Mcp From Remote Url logo

Add Mcp From Remote Url

Organization
speakeasy-api
add-mcp-from-remote-url

Add a user-supplied remote MCP server URL to an explicit AICP project through the Speakeasy AI Control Plane Platform MCP.

Overview

Publisherspeakeasy-api
Repositorygram
Skill nameadd-mcp-from-remote-url
Stars
269
Forks
33
Bundled files
Instructions only
LicenseAGPL-3.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by speakeasy-api on GitHub. Read the source before you install it.

Installation

Install the Add Mcp From Remote Url AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/speakeasy-api/gram.git /tmp/gram
mkdir -p .claude/skills
cp -r /tmp/gram/server/internal/plugins/platform_mcp_skills/add-mcp-from-remote-url .claude/skills/add-mcp-from-remote-url
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Add Mcp From Remote Url in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Add Mcp From Remote Url on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Add Mcp From Remote Url is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Add an MCP from a remote URL

Use this workflow only through the authenticated Speakeasy AI Control Plane (AICP) Platform MCP when the user supplies a remote MCP server URL that is not in the reviewed MCP Catalogue. It follows the same guarded outcome a user completes in the AICP dashboard: inspect the URL, confirm the bounded evidence and project, register privately, finish secure setup, and verify readiness. For a reviewed catalogue entry, use add-mcp-from-catalog instead. The package itself grants no organization access.

Safety rules

  • Never ask the user to paste API keys, passwords, access or refresh tokens, OAuth codes, client secrets, secret headers, or MCP credentials into chat. Authentication and headers are configured only through secure AICP dashboard setup.
  • Use inspect_mcp_candidate as the only read-only inspection step for a user-supplied URL. It returns bounded evidence and does not register or distribute anything.
  • Keep the target project explicit. Never infer it from a previous conversation or silently substitute another project.
  • Before registration, show the user the returned URL, transport, tool count and names, authentication posture, setup requirement, and OAuth-discovery state. State any missing evidence honestly.
  • Register only after the user explicitly confirms this exact remote server and project. Registration revalidates and re-inspects the URL; an earlier inspection is never trusted as admission evidence.
  • Registration is private. Do not claim the server is available to users until fresh readiness succeeds and exact-plugin distribution is rollout-enabled.
  • Show non-secret setup and authorization URLs only when a Platform MCP tool returns them.
  • Use send_platform_mcp_feedback only after asking for consent, and never include identifiers, URLs, credentials, payloads, headers, logs, or attachments.

Workflow

  1. Call list_projects to verify that the Platform MCP is authenticated and obtain eligible projects. If discovery is unavailable, stop and ask the user to complete or repair AICP OAuth.
  2. If the user names a product that could be in the reviewed catalogue, call search_mcp_catalog by name before handling the URL. Prefer an exact reviewed candidate when available.
  3. Call inspect_mcp_candidate with remote_url set to the user's exact URL. Do not supply catalogue selectors at the same time.
  4. Present the returned bounded evidence. Ask the user to explicitly confirm registering this exact URL in one exact project. If inspection reports an error or unavailable evidence, do not retry unchanged input or claim registration succeeded.
  5. After confirmation, call register_remote_mcp with the exact project, URL, optional safe display name, and a fresh idempotency key. This re-inspects the URL and creates private project configuration only.
  6. If this workflow is running in a managed project assistant, present the returned dashboard setup URL when one exists, and call get_mcp_readiness without force to report the persisted, actor-scoped evidence. Never force a provider probe from an assistant. A freshly registered MCP normally has no persisted evidence yet and reports readiness_unavailable; that is not a reason to stop. Provider attachment does not depend on readiness evidence: when inspection reported authentication_required, ask for explicit confirmation, call attach_platform_mcp_identity_provider, present its exact authorization URL, and wait for the user to use Connect or Authorize there. When inspection reported anonymous, the endpoint needs no upstream identity provider — skip attachment and continue.
  7. For an external Platform MCP client, if next_action is secure_dashboard_setup_required, present the exact dashboard_setup_url. The user completes authentication or secret entry outside chat; never request the resulting value.
  8. For an external Platform MCP client, call get_mcp_readiness with the selected project and returned registration ID. For a non-ready result, follow only its server-provided repair action. When it requires provider attachment, ask for explicit confirmation before attach_platform_mcp_identity_provider, then present its exact authorization URL.
  9. For an external Platform MCP client, after secure setup or authorization, call get_mcp_readiness with force: true. Do not rely on stale or inferred readiness.
  10. For an external Platform MCP client, when readiness is current and ready, report the server-returned evidence. Registration remains private until a separately rollout-gated exact-plugin distribution is available.
  11. Call get_mcp_client_admission for the same project and registration ID and report the mode it returns together with the custom client ID metadata URLs it lists, which together decide which MCP clients may authorize against this server. Change it only when the user asks: explain what the proposed mode admits and refuses, ask for explicit confirmation, then call set_mcp_client_admission with that exact mode and confirmed: true. Known clients (presets) refuses an unlisted client at authorization with no fallback.

OAuth consent, secret entry, and provider authorization are the expected out-of-agent stops. URL and project selection, registration confirmation, and provider-attachment confirmation stay in the conversation.

Frequently asked questions

What does the Add Mcp From Remote Url AI skill do?

Add a user-supplied remote MCP server URL to an explicit AICP project through the Speakeasy AI Control Plane Platform MCP.

Why use Add Mcp From Remote Url on TypingMind?

Because you install it once and use it with any model. Add Mcp From Remote Url is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Add Mcp From Remote Url in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/speakeasy-api/gram/tree/main/server/internal/plugins/platform_mcp_skills/add-mcp-from-remote-url. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Add Mcp From Remote Url?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Add Mcp From Remote Url?

As many as you like. As long as a model supports skills, you can use Add Mcp From Remote Url with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Add Mcp From Remote Url AI skill free?

Yes. It is published on GitHub by speakeasy-api under the AGPL-3.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇