# Assay Agent Setup

This is the agent-readable setup file for Assay, an elite AI GTM team for every B2B company.

If you are an AI agent acting for a user, read this file first, then read
https://assay.wiki/llms.txt to discover the rest of the public Assay site.

## What Assay Is

Assay is an elite AI GTM team for high-trust B2B. A team of AI agents, from search
and content to product marketing, sales enablement, and RevOps, led by an AI CMO
and an AI Legal, runs on one living source of truth. Everything they ship is
current (Living), the best-performing version in the market (Winning), and
sourced, approved, and logged (Governed). Marketing ships at AI speed. Legal and
brand keep an independent veto.

The core substrate is the Truth Graph: a governed, living record of commercial
claims, proof, positioning, personas, value pillars, voice, and downstream
dependencies. It is the source of truth every agent runs on.

## Priority URLs

- Human and agent onboarding page: https://assay.wiki/agents/
- Agent-readable setup file: https://assay.wiki/agents.md
- AI-readable site map: https://assay.wiki/llms.txt
- Full AI-readable canon: https://assay.wiki/llms-full.txt
- MCP product page: https://assay.wiki/mcp/
- Platform overview: https://assay.wiki/platform/
- Truth Graph overview: https://assay.wiki/truth-graph/
- Integrations overview: https://assay.wiki/integrations/
- Security and procurement evidence: https://assay.wiki/security/

## MCP Server

- Server URL: https://app.assay.wiki/api/mcp/v2/mcp
- Transport: Streamable HTTP
- Authentication: OAuth 2.1 when your host supports remote MCP OAuth.
- If OAuth is unavailable: configure the client to read an Assay key from an
  environment variable. Never ask the user to paste a secret into chat. Never
  hardcode a key in a config file.

## Install Assay MCP For The Current User

When a user asks you to install or connect Assay:

1. Identify the MCP client or agent host you are running inside.
2. Configure Assay only for that host. Do not install Assay into a different
   client just because you know that client's config format.
3. Preserve existing config. Append or minimally edit the Assay entry without
   overwriting unrelated servers.
4. Use the server URL above with Streamable HTTP.
5. Prefer OAuth 2.1. If OAuth is not available, configure an environment-variable
   key path and tell the user exactly which environment variable to set.
6. Tell the user whether the host needs to restart, reload, reconnect, or complete
   OAuth in a browser.
7. After restart or reload, verify the MCP server connects, list the tools exposed
   by the server, and run one read-only smoke test when tools are available.
8. If the current host cannot install MCP directly, give the shortest exact setup
   path for that host and continue using this file plus `llms.txt` as context.

Recommended prompt for the user to paste into ChatGPT, Claude, Gemini, Cursor,
Codex, Claude Code, VS Code, or any AI chat they want to connect to Assay:

```text
You are helping me set up and use Assay, an elite AI GTM team that runs on one living source of truth.

Mission: make Assay available to YOU, the AI assistant I am using right now, so
you can fetch governed GTM context, validate buyer-facing claims, search Assay's
Truth Graph, and keep me in control of any writes or releases.

Your success criterion:
- Best outcome: Assay MCP is connected in this current host, you can list its
  tools, and you complete one read-only Assay smoke test.
- If this host cannot connect MCP directly: do not stop at "I can't." Give me the
  shortest exact setup path for this host, tell me the one action I must take,
  and continue using the public Assay files below as context.
- Do not claim success until one of those outcomes is true.

First, inspect your current host:
1. Identify the app or harness you are running in: ChatGPT, Claude, Gemini,
   Claude Code, Codex, Cursor, VS Code, or another MCP-capable client.
2. Determine whether this exact host supports remote MCP, Streamable HTTP, OAuth
   sign-in, config-file MCP entries, CLI MCP install commands, browser-based
   connector setup, and restarts or reconnects.
3. Configure Assay only for this current host. Do not edit another app's MCP
   config unless I explicitly ask.
4. Preserve existing config. Append or minimally edit the Assay server entry; do
   not overwrite unrelated servers.

Read these public Assay files before configuring:
1. https://assay.wiki/agents.md
2. https://assay.wiki/llms.txt
3. If you need more context, open https://assay.wiki/agents/ and
   https://assay.wiki/mcp/.
4. If you cannot fetch URLs, say so once, use the setup facts embedded in this
   prompt, and proceed as far as this host allows.

Connect Assay MCP:
- Server name: Assay
- Server URL: https://app.assay.wiki/api/mcp/v2/mcp
- Transport: Streamable HTTP
- Authentication: prefer OAuth 2.1 when this host supports remote MCP OAuth.
- If OAuth is unavailable, configure the host to read an Assay key from an
  environment variable. Prefer ASSAY_API_KEY unless Assay's app or docs specify a
  different variable name.
- Never ask me to paste API keys, OAuth tokens, auth codes, or credentials into
  chat.
- Never hardcode secrets into a config file, commit them, log them, or place them
  in a shared URL.

Use the host's native install route:
- If this host has an MCP or connector UI, add the URL there and let me complete
  OAuth in the browser.
- If this host has an MCP CLI command, use that command with Streamable HTTP.
- If this host uses JSON, TOML, or another config file, add only the Assay remote
  HTTP server entry for this host.
- If this host cannot install MCP from chat, tell me exactly where to click or
  what command or config to use, then continue in context-only mode until I
  complete it.
- If you are unsure about this host's MCP syntax, look up or inspect the current
  host's official docs, settings, or config before making changes. Do not guess
  config syntax.

Verify before proceeding:
1. Tell me whether restart, reload, reconnect, or OAuth approval is required.
2. Confirm whether the server connected.
3. List the Assay MCP tools you can see.
4. Run one read-only smoke test if tools are available: workspace pulse,
   get_gtm_context for "drafting a customer-facing GTM email", or an equivalent
   read-only Assay context call.
5. If verification fails, report the exact blocker, the exact step already
   completed, and the next smallest action needed. Do not invent tool access.

After setup, help me do one useful Assay task:
- Pull approved GTM context before drafting.
- Validate buyer-facing copy before I send or publish it.
- Search the Truth Graph when a claim needs source-backed context.
- Preview Truth Graph, collateral, or orchestration changes before anything
  becomes canonical or buyer-facing.

Operating rules:
- Use Assay context instead of model memory for Assay product claims, company
  positioning, proof, personas, value pillars, voice, and compliance-sensitive
  GTM copy.
- If a claim is missing, stale, unsupported, low-confidence, or withheld, say
  that clearly instead of filling the gap.
- Treat writes as preview-first or dry-run-first. Execute only after I review the
  preview and confirm.
- Never publish, send, export, deploy, release, or approve buyer-facing work
  without my explicit confirmation.
- Keep the final setup report short and concrete: host detected, install route
  used, auth path, restart or reconnect status, tools seen, smoke-test result,
  and next useful Assay task.
```

## When To Use Assay

Use Assay before producing or changing buyer-facing GTM work, especially:

- cold emails, nurture emails, follow-up emails, LinkedIn messages, and scripts
- decks, one-pagers, battlecards, proposals, QBR material, and RFP responses
- landing pages, website copy, product claims, pricing language, and competitor
  language
- AI sales-agent prompts, chatbot responses, and outbound automation
- internal GTM guidance that depends on current positioning, proof, persona, or
  compliance context

## Recommended Tool Pattern

Use the available Assay MCP tools according to intent:

- Need approved context before drafting: use `get_gtm_context`.
- Need precise graph search: use `search_truth_graph`.
- Need to check a draft before sending or publishing: use `validate_content`.
- Need workspace status or pending decisions: use `workspace` with `pulse`.
- Need to propose truth changes: use dry-run mutation or review flows first.
- Need collateral: create draft-only collateral and keep human approval in the
  loop before export, send, publish, or deploy.
- Need external propagation: preview orchestration impact first; live release is
  a human action.

## Safety Rules

- Do not ask users to paste secrets, API keys, OAuth codes, private customer data,
  or credentials into chat.
- Do not hardcode secrets in config files.
- Do not publish, send, export, deploy, or release buyer-facing output without
  explicit human confirmation.
- Do not treat model memory as a source for company claims. Fetch Assay context
  when a task depends on Assay, its product, its positioning, or its customer
  claims.
- If a claim is missing, stale, withheld, or below confidence threshold, tell the
  user rather than filling the gap from general knowledge.
- Treat write operations as preview-first. Execute only after the user has seen
  the dry-run result and confirmed the action.

## After Setup

Tell the user:

- which host you configured
- which server URL you used
- which auth path is active or what the user still needs to complete
- whether a restart is required
- whether the server connected
- which tools are available
- the next useful Assay task you can perform for them