# Lightsage

- [Quickstart](https://lightsage.com/docs/index.md): Set up Lightsage access, choose a client, and pull your first agent-ready work item.
- [Migrate from Sapient to Lightsage](https://lightsage.com/docs/migration-guide.md): Update Sapient CLI, MCP, Public API, Agent Tracker, and Docs Agent integrations to their Lightsage names.
- [Onboard your AI agent to Lightsage](https://lightsage.com/docs/agent-onboarding.md): Give your coding agent Lightsage skills, connected tools, workflows, and current documentation.
- [Agent Skills](https://lightsage.com/docs/agent-onboarding/agent-skills.md): Install three Lightsage Agent Skills in a compatible coding agent.
- [Lightsage MCP](https://lightsage.com/docs/agent-onboarding/lightsage-mcp.md): Connect a compatible AI client to the hosted Lightsage MCP server.
- [Lightsage CLI](https://lightsage.com/docs/agent-onboarding/lightsage-cli.md): Install the Lightsage CLI, authenticate your coding agent, and verify access.
- [Workflows](https://lightsage.com/docs/agent-onboarding/workflows.md): Use repeatable prompts that help your coding agent act on Lightsage findings.
- [Docs for agents](https://lightsage.com/docs/agent-onboarding/docs-for-agents.md): Give your AI agent current Lightsage documentation in a machine-readable format.
- [Pull actionables into your agent](https://lightsage.com/docs/workflows/pull-actionables-into-your-agent.md): Copy a prompt that has your coding agent pull your Lightsage tasks and opportunities and ship fixes for them.
- [Running evals](https://lightsage.com/docs/guides/running-evals.md): Create, fan out, monitor, and inspect coding-agent evals with the Lightsage CLI.
- [Measure agent-attributed growth](https://lightsage.com/docs/agent-analytics/attributed-growth.md): Connect visits from recognized AI agent sources to sign-up, demo, checkout, and activation milestones in Agent Analytics.
- [Google Cloud DNS integration](https://lightsage.com/docs/agent-analytics/integrations/google-cloud-dns.md): Set up Lightsage Agent Analytics for a domain managed in Google Cloud DNS by routing traffic through a Google load balancer and exporting request logs.
- [Lightsage Docs Agent](https://lightsage.com/docs/lightsage-docs-agent/overview.md): Run Lightsage docs evals from GitHub pull requests before documentation changes ship.
- [Run docs evals from GitHub](https://lightsage.com/docs/lightsage-docs-agent/github-pr-evals.md): Use Lightsage slash commands on GitHub pull requests to run docs evals against staging documentation.
- [CLI Reference](https://lightsage.com/docs/cli-reference/index.md): Install, authenticate, and navigate the Lightsage CLI.
- [Visibility](https://lightsage.com/docs/cli-reference/visibility.md): Retrieve visibility metrics, citations, competitors, and prompt reports from the Lightsage CLI.
- [Opportunities](https://lightsage.com/docs/cli-reference/opportunities.md): List and retrieve ranked visibility opportunities from the Lightsage CLI.
- [Tasks](https://lightsage.com/docs/cli-reference/tasks.md): List, retrieve, and update daily tasks from the Lightsage CLI.
- [Prompts](https://lightsage.com/docs/cli-reference/prompts.md): Create, list, retrieve, update, and delete Visibility prompts from the Lightsage CLI.
- [Prompt topics](https://lightsage.com/docs/cli-reference/prompt-topics.md): List and manage Visibility prompt topics from the Lightsage CLI.
- [Prompt runs](https://lightsage.com/docs/cli-reference/prompt-runs.md): List and retrieve stored prompt runs from the Lightsage CLI.
- [Content](https://lightsage.com/docs/cli-reference/content.md): Generate drafts, finalize articles, and retrieve content from the Lightsage CLI.
- [Site audits](https://lightsage.com/docs/cli-reference/site-audit.md): Retrieve the latest website audit and inspect individual audited pages from the Lightsage CLI.
- [Evals](https://lightsage.com/docs/cli-reference/evals.md): Create and manage reusable coding-agent simulations from the Lightsage CLI.
- [Eval runs](https://lightsage.com/docs/cli-reference/eval-runs.md): Start saved or direct eval runs and inspect their lifecycle state from the Lightsage CLI.
- [Eval results](https://lightsage.com/docs/cli-reference/eval-results.md): List and retrieve completed eval results from the Lightsage CLI.
- [Agents](https://lightsage.com/docs/cli-reference/agents.md): List available coding agents for eval runs from the Lightsage CLI.
- [Repositories](https://lightsage.com/docs/cli-reference/repositories.md): Manage Git repository workspaces for eval configurations from the Lightsage CLI.
- [Environments](https://lightsage.com/docs/cli-reference/environments.md): List reusable runtime environments from the Lightsage CLI.
- [MCP servers](https://lightsage.com/docs/cli-reference/mcp-servers.md): List reusable MCP server integrations from the Lightsage CLI.
- [CLIs](https://lightsage.com/docs/cli-reference/clis.md): List reusable CLI tools from the Lightsage CLI.
- [Skills](https://lightsage.com/docs/cli-reference/skills.md): List reusable skills available to workflows and eval configurations from the Lightsage CLI.
- [Lightsage MCP](https://lightsage.com/docs/mcp-reference/index.md): Choose a client and connect Lightsage MCP to coding agents and MCP-capable tools.
- [Install Lightsage MCP in ChatGPT](https://lightsage.com/docs/mcp-reference/chatgpt.md): Connect ChatGPT developer mode to Lightsage MCP with a preconfigured public OAuth client.
- [Install Lightsage MCP in Claude](https://lightsage.com/docs/mcp-reference/claude.md): Connect Claude hosted connector surfaces to Lightsage MCP with OAuth.
- [Install Lightsage MCP in Claude Code](https://lightsage.com/docs/mcp-reference/claude-code.md): Connect Claude Code to Lightsage MCP with a remote HTTP server and the X-Lightsage-Api-Key header.
- [Install Lightsage MCP in Codex](https://lightsage.com/docs/mcp-reference/codex.md): Connect Codex to Lightsage MCP with a streamable HTTP server in config.toml.
- [Install Lightsage MCP in Cursor](https://lightsage.com/docs/mcp-reference/cursor.md): Connect Cursor to Lightsage MCP with OAuth or an API key.
- [Install Lightsage MCP in Gemini CLI](https://lightsage.com/docs/mcp-reference/gemini-cli.md): Connect Gemini CLI to Lightsage MCP with a streamable HTTP MCP server.
- [Install Lightsage MCP in GitHub Copilot](https://lightsage.com/docs/mcp-reference/github-copilot.md): Connect GitHub Copilot to Lightsage MCP from VS Code or Copilot CLI.
- [Install Lightsage MCP in Kilo](https://lightsage.com/docs/mcp-reference/kilo.md): Connect Kilo to Lightsage MCP with a remote MCP server entry.
- [Install Lightsage MCP in OpenCode](https://lightsage.com/docs/mcp-reference/opencode.md): Connect OpenCode to Lightsage MCP with a remote MCP server entry.
- [API Reference](https://lightsage.com/docs/api-reference/introduction.md): Authenticate and call the Lightsage public API from your own integrations.
- [Get Status](https://lightsage.com/docs/api-reference/status/get-status.md): Checks API liveness without authentication. Use `GET /v2/auth/status` to validate an API key.
- [Get Auth Status](https://lightsage.com/docs/api-reference/status/get-auth-status.md): Validates the API key and returns its organization ID, API key ID, scopes, and authentication status.
- [Retrieve Current Visibility](https://lightsage.com/docs/api-reference/visibility/retrieve-current-visibility.md): Returns recommendation score, visibility score, ranks, and date-range metadata for the configured primary company. Metrics are computed from active prompts only; when no data exists, values are `null`.
- [Retrieve Visibility Overview](https://lightsage.com/docs/api-reference/visibility/retrieve-visibility-overview.md): Returns aggregate snapshot, daily trends, per-platform breakdowns, and competitor comparison. Calculated from active prompts only.
- [List Top Cited Urls](https://lightsage.com/docs/api-reference/visibility/list-top-cited-urls.md): Returns URL-level citation counts ranked from most to least cited. Results can be filtered by platform and to owned or external sources.
- [Retrieve Prompt Visibility Report](https://lightsage.com/docs/api-reference/visibility/retrieve-prompt-visibility-report.md): Returns per-topic and per-prompt visibility metrics including recommendation score, rank, visibility score, average position, and citation counts.
- [List Prompts](https://lightsage.com/docs/api-reference/prompts/list-prompts.md): Returns active and inactive prompts by default. Set `include_archived` to include archived prompts.
- [Create Prompts](https://lightsage.com/docs/api-reference/prompts/create-prompts.md): Creates prompts in a batch. Each item is validated independently, so the response can contain both created prompts and individual errors.
- [List Topics](https://lightsage.com/docs/api-reference/prompts/list-topics.md): Returns all prompt topics available to the organization.
- [Create Topic](https://lightsage.com/docs/api-reference/prompts/create-topic.md): Creates a prompt topic and returns the saved topic.
- [Delete Topic](https://lightsage.com/docs/api-reference/prompts/delete-topic.md): Archives a prompt topic. Set `archive_prompts` to archive remaining prompts; otherwise the request fails with `400` if prompts remain.
- [Update Topic](https://lightsage.com/docs/api-reference/prompts/update-topic.md): Renames a prompt topic and returns the updated topic.
- [List Prompt Runs](https://lightsage.com/docs/api-reference/prompts/list-prompt-runs.md): Returns stored prompt runs with limit-and-offset pagination, without exposing raw runtime or provider configuration. Filter by prompt, platform, or date range.
- [Run Prompts](https://lightsage.com/docs/api-reference/prompts/run-prompts.md): Queue saved prompts using the organization's configured targets.
- [Get Prompt Run Status](https://lightsage.com/docs/api-reference/prompts/get-prompt-run-status.md): Return status and progress for a queued prompt run.
- [Retrieve Prompt Run](https://lightsage.com/docs/api-reference/prompts/retrieve-prompt-run.md): Returns one stored prompt run, including mentions, citations, and any sanitized coding-agent trace captured for the run.
- [Retrieve Prompt](https://lightsage.com/docs/api-reference/prompts/retrieve-prompt.md): Returns a prompt with its topic, platforms, tags, lifecycle status, and coding-agent run settings.
- [Delete Prompt](https://lightsage.com/docs/api-reference/prompts/delete-prompt.md): Archives the prompt and excludes it from normal listings while preserving its historical run data.
- [Update Prompt](https://lightsage.com/docs/api-reference/prompts/update-prompt.md): Updates a prompt's text, topic, platforms, lifecycle status, or coding-agent run settings. Omitted fields remain unchanged.
- [List Opportunities](https://lightsage.com/docs/api-reference/opportunities/list-opportunities.md): Returns ranked opportunities computed from stored prompt visibility results. Each includes an `execution_prompt` with context for an AI agent. Default window is 30 days.
- [Retrieve Opportunity](https://lightsage.com/docs/api-reference/opportunities/retrieve-opportunity.md): Returns one computed opportunity and its execution context for the selected date window.
- [List Tasks](https://lightsage.com/docs/api-reference/tasks/list-tasks.md): Returns persisted daily tasks with execution instructions. Includes per-status counts not narrowed by the `status` filter.
- [Retrieve Task](https://lightsage.com/docs/api-reference/tasks/retrieve-task.md): Returns one persisted task and its execution prompt.
- [Update Task](https://lightsage.com/docs/api-reference/tasks/update-task.md): Updates a task's status, priority, assignee, or action type. Only sent fields are changed; omitted fields remain unchanged.
- [List Site Audits](https://lightsage.com/docs/api-reference/site-audits/list-site-audits.md): Returns every audited page and its actionable issues. Each page includes its score, priority, issue descriptions, evidence, and recommended fixes. This reads existing data and does not start a crawl.
- [Retrieve Site Audit](https://lightsage.com/docs/api-reference/site-audits/retrieve-site-audit.md): Returns one audited page with its score, priority, supporting evidence, and recommended fixes.
- [List Evals](https://lightsage.com/docs/api-reference/evals/list-evals.md): Returns all active eval definitions owned by the organization. Agent Preference evals are not included; list them with `GET /v2/agent-preference/evals`.
- [Create Eval](https://lightsage.com/docs/api-reference/evals/create-eval.md): Creates a reusable simulation definition with one or more task prompts and judges. Optional agents, persona, CLI installations, MCP servers, setup commands, cleanup commands, grounding policy, repeat count, and tags are saved with the eval. `search_grounding` supports `disabled`, `enabled`, and `def…
- [Create evals from a template](https://lightsage.com/docs/api-reference/evals/create-evals-from-a-template.md): Step 2 of the reusable template workflow. Provide the `id` and `version` returned by `POST /v2/eval-templates` as `template_id` and `expected_template_version`, then provide only prompt-specific fields in `evals`. The template supplies only the settings named in its `included_components`; omitted se…
- [Retrieve Eval](https://lightsage.com/docs/api-reference/evals/retrieve-eval.md): Returns one reusable eval simulation definition.
- [Delete Eval](https://lightsage.com/docs/api-reference/evals/delete-eval.md): Permanently deletes an eval and all of its saved configurations.
- [Update Eval](https://lightsage.com/docs/api-reference/evals/update-eval.md): Updates a reusable eval simulation definition. Omitted fields remain unchanged. Empty `agent`, `clis`, `mcps`, `setup_commands`, `cleanup_commands`, or `tags` arrays clear those collections, and `persona: null` clears the saved persona.
- [List Configurations](https://lightsage.com/docs/api-reference/evals/list-configurations.md): Returns the saved runtime configurations for an eval, including repository, environment, and tool selections.
- [Create Configuration](https://lightsage.com/docs/api-reference/evals/create-configuration.md): Creates a saved runtime configuration that pairs an eval with a repository, environment, and selected tools.
- [Retrieve Configuration](https://lightsage.com/docs/api-reference/evals/retrieve-configuration.md): Returns one saved configuration for an eval.
- [Delete Configuration](https://lightsage.com/docs/api-reference/evals/delete-configuration.md): Permanently deletes an eval configuration and returns its last saved state.
- [Update Configuration](https://lightsage.com/docs/api-reference/evals/update-configuration.md): Updates an eval configuration; omitted fields remain unchanged.
- [List Eval templates](https://lightsage.com/docs/api-reference/eval-templates/list-eval-templates.md): Returns active reusable Eval templates owned by the authenticated organization. Templates contain reusable configuration and never task prompts.
- [Create an Eval template](https://lightsage.com/docs/api-reference/eval-templates/create-an-eval-template.md): Step 1 of the reusable template workflow. Creates an organization-owned Eval template containing only the configuration components selected in `included_components`. Do not include task prompts in the template. The response returns the template `id` and `version`; pass them as `template_id` and `exp…
- [Retrieve an Eval template](https://lightsage.com/docs/api-reference/eval-templates/retrieve-an-eval-template.md): Returns one active reusable Eval template.
- [Delete an Eval template](https://lightsage.com/docs/api-reference/eval-templates/delete-an-eval-template.md): Soft-deletes an Eval template. Evals previously created from it remain independent and continue to run with their copied configuration.
- [Update an Eval template](https://lightsage.com/docs/api-reference/eval-templates/update-an-eval-template.md): Updates an Eval template. Supply `expected_template_version` to reject an edit based on stale data. Existing evals are never changed.
- [List Runs](https://lightsage.com/docs/api-reference/eval-runs/list-runs.md): Returns custom eval runs, ordered newest first, with lifecycle state and progress. Includes scheduled, onboarding, and pull request runs and runs started in the Lightsage app, as well as runs started through `POST /v2/eval-runs`.
- [Start an eval run](https://lightsage.com/docs/api-reference/eval-runs/start-an-eval-run.md): Queues a durable eval job and returns immediately with a polling ID. Poll `GET /v2/eval-runs/{run_id}` until its status reaches a terminal value; once finished it also returns the results and analysis. Follow a run live with the monitor operation.
- [Cancel an eval run](https://lightsage.com/docs/api-reference/eval-runs/cancel-an-eval-run.md): Marks an active eval run as cancelled and prevents queued attempts from starting. Running sandbox attempts are stopped asynchronously. Requests already sent to an external provider cannot be recalled, but any later response does not change the run from cancelled. Repeating this request for an alread…
- [Monitor Runs](https://lightsage.com/docs/api-reference/eval-runs/monitor-runs.md): Streams an immediate snapshot followed by live status and sanitized activity. Provide `run_id` to monitor one eval run, or omit it to capture all active runs when the connection opens.
- [Retrieve an eval run trace](https://lightsage.com/docs/api-reference/eval-runs/retrieve-an-eval-run-trace.md): Returns a finite page of sanitized execution events for one eval run. Use `next_after_id` as `after_id` to retrieve the next page. Use the monitor operation instead when following a run live.
- [Retrieve an eval run](https://lightsage.com/docs/api-reference/eval-runs/retrieve-an-eval-run.md): Returns the run's current status and progress. Once its attempts finish, the response also includes their results and analysis. Poll this until the status reaches a terminal value. Use the trace operation for the raw execution event log, or the monitor operation to follow a run live.
- [List Competitors](https://lightsage.com/docs/api-reference/agent-preference/list-competitors.md): Returns the tracked competitors your company can be compared against. Use a returned `id` as `competitor_id` when creating an Agent Preference eval.
- [Retrieve Head To Head](https://lightsage.com/docs/api-reference/agent-preference/retrieve-head-to-head.md): Returns how often agents recommended your company over each tracked competitor: wins, losses, ties, and win rate per competitor plus a combined record. Calculated from the most recent attempts across all Agent Preference evals, up to `limit`; `truncated` reports whether older attempts were left out.
- [List Evals](https://lightsage.com/docs/api-reference/agent-preference/list-evals.md): Returns all active Agent Preference evals owned by the organization.
- [Create Eval](https://lightsage.com/docs/api-reference/agent-preference/create-eval.md): Creates a head-to-head comparison between your company and one tracked competitor. Each prompt asks an agent to choose, and a fixed judge records which company it recommended. Creating the eval does not start a run; pass the returned `id` as `eval_id` to `POST /v2/eval-runs`.
- [Retrieve Eval](https://lightsage.com/docs/api-reference/agent-preference/retrieve-eval.md): Returns one Agent Preference eval.
- [Delete Eval](https://lightsage.com/docs/api-reference/agent-preference/delete-eval.md): Permanently deletes an Agent Preference eval and returns its last saved state.
- [Update Eval](https://lightsage.com/docs/api-reference/agent-preference/update-eval.md): Updates an Agent Preference eval. Omitted fields remain unchanged, an empty `agent` or `tags` array clears that collection, and `persona: null` clears the saved persona. The competitor and the judge that decides the comparison cannot be changed.
- [List Results](https://lightsage.com/docs/api-reference/agent-preference/list-results.md): Returns recorded attempts for an Agent Preference eval, newest first, each with whether your company won, lost, or tied against the competitor.
- [List Agents](https://lightsage.com/docs/api-reference/agents/list-agents.md): Returns the harness-and-model combinations your plan can run, as single agent IDs for use in eval runs.
- [List Repositories](https://lightsage.com/docs/api-reference/repositories/list-repositories.md): Returns built-in templates and enabled saved Git repositories. Pass an item's `id` directly as `repository` in a direct eval run. Public GitHub URLs are also accepted by eval runs but are not included in this list.
- [Create Repository](https://lightsage.com/docs/api-reference/repositories/create-repository.md): Adds a reusable Git repository workspace for eval configurations.
- [Retrieve Repository](https://lightsage.com/docs/api-reference/repositories/retrieve-repository.md): Returns one reusable repository workspace.
- [Delete Repository](https://lightsage.com/docs/api-reference/repositories/delete-repository.md): Permanently deletes a repository workspace and returns its last saved state.
- [Update Repository](https://lightsage.com/docs/api-reference/repositories/update-repository.md): Updates a repository workspace; omitted fields remain unchanged.
- [List Environments](https://lightsage.com/docs/api-reference/environments/list-environments.md): Returns reusable environments without exposing secret values.
- [List Mcp Servers](https://lightsage.com/docs/api-reference/mcp-servers/list-mcp-servers.md): Returns reusable MCP servers without exposing credentials or secret values.
- [List Clis](https://lightsage.com/docs/api-reference/clis/list-clis.md): Returns reusable CLIs without exposing setup or installation commands.
- [List Skills](https://lightsage.com/docs/api-reference/skills/list-skills.md): Returns reusable skills available to workflows and eval configurations.
- [Changelog](https://lightsage.com/docs/changelog.md): Developer-facing Lightsage CLI and public API changes.
- [How Lightsage credits work and how to estimate usage](https://lightsage.com/docs/account/credits.md): Learn how Lightsage credits work, what each platform type costs per run, and how to estimate your monthly usage before choosing a plan.
- [Frequently asked questions about Lightsage](https://lightsage.com/docs/account/faq.md): Answers to common questions about Lightsage's AEO platform, supported AI platforms, credit system, billing, and how to get started tracking your API.
- [Lightsage pricing: Free, Pro, and Enterprise plans](https://lightsage.com/docs/account/plans.md): Compare Free, Pro, and Enterprise plans to find the right fit for tracking and improving your API's visibility across AI coding agents.
- [AGENTS](https://lightsage.com/docs/AGENTS.md)
- [Agent Tracking: See Which AI Agents Visit Your Docs](https://lightsage.com/docs/features/agent-tracking.md): Add one line of middleware to detect AI coding agent visits to your website and documentation in real time, with zero performance impact.
- [API Performance: Benchmark How Agents Use Your API](https://lightsage.com/docs/features/api-performance.md): Benchmark how AI coding agents discover, call, and execute your API endpoints. See letter grades, per-endpoint pass rates, and actionable fixes across agents.
- [Opportunities Engine: AI-Powered Visibility Insights](https://lightsage.com/docs/features/opportunities-engine.md): Automatically surface competitor gaps, quick wins, content opportunities, and technical fixes ranked by impact and effort across your AI visibility data.
- [Visibility Analytics: Track Your AI Brand Presence](https://lightsage.com/docs/features/visibility-analytics.md): Monitor your brand mention rate, share of voice, and average position across 17 AI platforms—including coding agents, answer engines, and frontier models.
- [Detect AI agent visits with agent tracking middleware](https://lightsage.com/docs/guides/agent-tracking-middleware.md): Install Lightsage's lightweight middleware on Next.js, Vercel, Cloudflare, Express, Astro, or Netlify to detect coding agent visits to your docs in real time.
- [Add llms.txt to improve coding agent discoverability](https://lightsage.com/docs/guides/llms-txt.md): Create a machine-readable API description at your domain root to give coding agents immediate context about what your API does and how to make their first call.
- [Build an MCP server for direct coding agent access](https://lightsage.com/docs/guides/mcp-servers.md): Learn what the Model Context Protocol is, what makes a high-scoring MCP server, and how to submit your server to Devtool Arena for public benchmarking.
- [Optimize your API for AI coding agent discovery](https://lightsage.com/docs/guides/optimize-for-agents.md): Work through the 4-layer coding agent decision stack — training data, web search, context retrieval, and tool execution — to boost your recommendation rate.
- [How to track coding agent recommendations for your API](https://lightsage.com/docs/guides/track-coding-agents.md): Learn which metrics matter for coding agent tracking, how to define implementation prompts in Lightsage, establish baselines, and read your dashboard effectively.
- [What is Lightsage? AI Engine Optimization for APIs](https://lightsage.com/docs/introduction.md): Lightsage tracks how AI coding agents discover and use your API across 17 platforms — so you can close the gap where developer adoption actually happens.
- [Key concepts: Lightsage terminology and metrics explained](https://lightsage.com/docs/key-concepts.md): Definitions for every term you'll encounter in Lightsage — from GEO and AEO to Visibility Score, API Performance, credits, llms.txt, and MCP.
- [Devtool Arena changelog: scores, companies, categories](https://lightsage.com/docs/leaderboard/changelog.md): A running record of all notable changes to the Devtool Arena leaderboard: new companies, new categories, new leaderboard types, and ranking updates.
- [Devtool Arena: the coding agent API leaderboard](https://lightsage.com/docs/leaderboard/overview.md): Devtool Arena is a free, public leaderboard benchmarking 85+ developer tools against AI coding agents across API, CLI, and MCP evaluation types.
- [How Devtool Arena scores are calculated](https://lightsage.com/docs/leaderboard/scoring.md): Learn how Eval Score and Discovery Score combine into an overall score, what the A–D grade thresholds mean, and what the checklist columns measure.
- [Submit your API to Devtool Arena for evaluation](https://lightsage.com/docs/leaderboard/submit-api.md): Learn how to submit your API or developer tool for a live Devtool Arena evaluation, what the process covers, and how to maximize your score before submitting.
- [Install Lightsage MCP in Hermes](https://lightsage.com/docs/mcp-reference/hermes.md): Connect Hermes to Lightsage MCP with a streamable HTTP MCP server config.
- [Install Lightsage MCP in Microsoft Copilot](https://lightsage.com/docs/mcp-reference/microsoft-copilot.md): Connect Lightsage MCP to Microsoft Copilot Studio agents.
- [Install Lightsage MCP in OpenClaw](https://lightsage.com/docs/mcp-reference/openclaw.md): Save Lightsage MCP in OpenClaw's MCP server registry.
- [Install Lightsage MCP in Perplexity](https://lightsage.com/docs/mcp-reference/perplexity.md): Connect Perplexity custom remote MCP connectors to Lightsage MCP.
- [Install Lightsage MCP in Pi](https://lightsage.com/docs/mcp-reference/pi.md): Connect Pi to Lightsage MCP with pi-mcp-extension.
- [Quickstart: get your first API evaluation in 10 min](https://lightsage.com/docs/quickstart.md): Create a free Lightsage account, add your API, run your first evaluation, and install agent tracking middleware to start measuring AI visibility.
- [Track prompts across answer engines and coding agents](https://lightsage.com/docs/workflows/track-prompts-across-ai-platforms.md): Learn how Lightsage runs prompts across answer engines and coding agents, what each run measures, and how to read the results.

## OpenAPI Specs

- [openapi](/docs/openapi.json)
- [openapi](/docs/openapi.yml)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.