ToolYour

com.toolyourPublished by toolyour.comOfficial publisherv1.0.1Updated Nov 2, 2026

Remote MCP: plan, run, verify for SEO/security/ship-gate. Same REST API key; 500 free credits/month.

VerifiedStreamable HTTPWeb executableProductivity & WorkflowDeveloper Tools

Overview

AI-generated overview

Remote ToolYour MCP gateway that lets an assistant plan a task, run a playbook or solve it, then verify results until a pass gate is reached.

What you can do
  • Plan, run and verify work: plan_task, run_playbook, solve_task, run_workflow and verify_task drive a plan-run-verify loop with a pass gate.
  • Recall stored context: recall_context recalls purpose-typed memory before a rebuild.
  • Check async jobs and identity: get_run polls runs by runId, and get_profile returns the authenticated account identity.
  • Manage saved playbooks (private beta): create, list, get, update and run named, versioned recipes and fetch their run receipts.
When to use it
Useful when you want an agent to work through repeatable engineering tasks such as SEO, security or ship-gate checks in a structured plan-run-verify loop, with the host editor, git and terminal kept in charge. Also relevant if you want to save a repeatable workflow as a named playbook for later runs.
Requirements
A remote Streamable HTTP endpoint; no local package is needed for the hosted service. Authentication is required: an OAuth flow plus an X-Api-Key header carrying a ToolYour API key (prefix ty_), the same key as the REST API. A free tier of 500 credits per month is mentioned. The saved-playbooks beta needs a private deployment with PLAYBOOKS_BETA=true.
Before you install
The API key is a secret sent in the X-Api-Key header and is the same credential as the REST API. Tool invocations consume credits (1–10 each) beyond the free monthly allowance, so usage can cost money. The agent is expected to apply changes in your workspace, so review what it writes. Saved playbooks are a private beta and are excluded from the public ChatGPT endpoint.

Installation

In SourceWeft

  1. Open ToolYour in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/com.toolyour%2Fmcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "toolyour": {
      "type": "http",
      "url": "https://api.toolyour.com/mcp/http"
    }
  }
}

README

Open-source ToolYour MCP

Remote MCP gateway for AI agents: plan → run playbook/solve → verify until pass.

MIT licensed. Hosted API/SaaS backends are optional — offline evals and local file control-plane run without them.

Product docs: https://www.toolyour.com/developers/mcp
Official registry: com.toolyour/mcp
npm client (separate): @toolyour/sdk (MIT)

Quick start

bash
cp .env.example .envnpm installnpm run build:registry   # from monorepo docs/ when regeneratingnpm run buildnpm run dev

Endpoints: http://localhost:3090/mcp (legacy SSE for compatible hosts) · Streamable HTTP: /mcp or /mcp/http. All Streamable HTTP endpoints are stateless: clients do not need session affinity, and a stale Mcp-Session-Id is ignored. The OAuth-protected /mcp/chatgpt endpoint validates its bearer token on every request. GET /mcp remains the legacy SSE endpoint and keeps its session behavior.

Health: GET /health/mcp · Ready: GET /health/mcp/ready · Metrics: GET /health/mcp/metrics (Prometheus text)

Auth

X-Api-Key: ty_...

Same key as ToolYour REST. Free tier: 500 credits/month (tools cost 1–10 credits). MCP exposes API-backed catalog tools only (hasApi).

Host contract

ToolYour does not replace Cursor/Claude. The host keeps editor, git, and terminal. Agents should:

  1. plan_task (free)
  2. run_playbook or solve_task
  3. Apply only rank-1 loop.nextActions in the workspace
  4. verify_task with prior result as baseline until loop.gate is pass (or stop)

Skill-loop responses also include an additive execution envelope (runId, intentId, intentType, idempotencyKey, and projectScope). Preserve it when handing a result to another MCP tool. Async jobs reuse execution.runId as the get_run polling id.

Internally, plan_task, solve_task, run_playbook, run_workflow, and verify_task use one executeIntent lifecycle boundary for correlation and the execution envelope. Credits settle on each gateway tool invoke (billing.settledBy = gateway_per_tool) — MCP does not double-bill. Free recall_context recalls purpose-typed memory before rebuilds.

Saved Playbooks (private beta)

Saved Playbooks turns a repeatable ToolYour workflow into a named, versioned recipe that an MCP-capable agent can run again. V1 deliberately points only to existing ToolYour skills or workflows; it does not store arbitrary shell commands, control another agent, or bypass host approval. Each account gets owner-scoped playbooks and durable run receipts.

Enable this only on a private/default MCP deployment with PLAYBOOKS_BETA=true. The beta adds create_saved_playbook, list_saved_playbooks, get_saved_playbook, update_saved_playbook, run_saved_playbook, and get_saved_playbook_run. It is intentionally excluded from /mcp/chatgpt so the reviewed public tool surface stays separate. The public surface includes the authenticated get_profile identity tool.

See Saved Playbooks beta design for the data model, safe execution boundary, and rollout guidance.

Offline evals (no API key)

bash
npm run ci                 # build + lint + unit/contract/integration + evalsnpm run eval:golden        # routing + jobReport fields + verify gatenpm run eval:playbooks     # skill → workflow → synthesizer matrix + fixture coveragenpm run golden:tier1       # host work-package shapes

Fixtures: tests/eval/synth-fixtures.json · Goals: tests/eval/goals.jsonl

Observability (open protocols)

SignalHow
JSON logsAlways (LOG_LEVEL)
In-process counters/health/mcp + /health/mcp/metrics
SpansSet OTEL_LOG_SPANS=1 and/or OTEL_EXPORTER_OTLP_ENDPOINT (OTLP/HTTP JSON → Collector / Jaeger / Tempo)

No proprietary APM required.

What stays hosted (optional)

  • Live tool execution via gateway + API key
  • Feature Memory / verification profiles (SaaS Mongo)
  • Redis for multi-replica async get_run

Local defaults use file-backed control-plane jobs.

License

MIT — see LICENSE.

Source: README.md at commit fabc0c2

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

1
  1. v1.0.1LatestSep 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts