Find Leads by Orthogonal: B2B Lead Discovery for Agents (2026)
Orthogonal Find Leads is a pay-per-call skill that gives AI agents instant B2B lead discovery. Works with Claude, Cursor, and all SKILL.md agents. $10 free.
Find Leads is Orthogonal's agent skill for B2B lead discovery. Point it at a target persona (job title, industry, company size, location) and your agent queries Orthogonal's 30+ data providers to return matching contacts. One API key covers everything. Pay-per-call with $10 free credits; compatible with Claude Code, Cursor, Windsurf, and all SKILL.md agents.
Orthogonal Find Leads is a SKILL.md-format agent skill built by Orthogonal (YC W26). It gives AI agents the ability to discover B2B leads by searching criteria like job title, industry, company size, and location across 30+ data providers. It runs on a single Orthogonal API key, starts free with $10 in credits, and works with Claude Code, Cursor, Windsurf, and any SKILL.md-compatible agent.
Maker: Orthogonal · Protocol: MCP · Auth: api key
Compatible agents: Claude Code, Claude Desktop (MCP), Cursor, Windsurf, GitHub Copilot, Codex CLI, OpenClaw, Any SKILL.md-compatible agent
Required runtime: Node.js >= 18 (for the Orthogonal CLI), ORTHOGONAL_API_KEY environment variable
About Orthogonal Find Leads
Orthogonal Find Leads is an agent skill built by Orthogonal (YC W26), a unified API gateway that launched in January 2026. The skill teaches any SKILL.md-compatible agent how to discover B2B prospects by submitting search criteria like job title, company size, industry, and location, then querying Orthogonal's catalog of 30+ integrated data providers including Apollo.io, People Data Labs, ContactOut, and Ocean.io. The result is a ranked list of matching contacts, ready for outreach or CRM import. The skill uses Orthogonal's custom SKILL.md format, a plain-text markdown spec that any AI coding agent reads natively. Under the hood, the agent calls the Orthogonal REST API or the hosted MCP server at mcp.orth.sh, authenticated with a single ORTHOGONAL_API_KEY that covers every provider in the catalog. There is no per-provider key management and no separate billing relationships to set up. The Orthogonal platform handles rate limiting, retries, and dynamic routing automatically. Find Leads works best inside automated GTM pipelines: a sales agent can identify 50 target CFOs at Series B fintech companies, hand the list to a lead-enrichment step for verified emails, then pass the enriched contacts to an outreach skill. The skill is compatible with Claude Code, Claude Desktop (via MCP), Cursor, Windsurf, GitHub Copilot, Codex CLI, and OpenClaw, covering all major agent environments as of June 2026. Orthogonal operates on a pay-as-you-go credit model with no monthly subscription. New accounts receive $10 in free credits, and each API call deducts credits based on the underlying data provider's per-record rate. An enterprise tier with custom credit packages is available for high-volume agent workloads. Orthogonal was founded by Christian Pickett (ex-Coinbase payments, ex-Vercel billing) and Bera Sogut (ex-Google reCAPTCHA and Maps, ex-Amazon Robotics) and is backed by Y Combinator W26. The platform has added over 30 named API partners since launching in January 2026 and ships new skill additions on a roughly weekly cadence.
Key Features
- Single key covers 30+ data providers: One ORTHOGONAL_API_KEY replaces Apollo.io, People Data Labs, ContactOut, and 27+ other B2B data subscriptions, eliminating per-provider onboarding.
- SKILL.md format works in every major agent: The skill installs as a plain-text SKILL.md file readable by Claude Code, Cursor, Windsurf, GitHub Copilot, and Codex CLI with no binary dependencies.
- MCP server for zero-install usage: Point any MCP-compatible client at https://mcp.orth.sh and the Find Leads capability is available immediately without running a local CLI.
- Pay-per-call with built-in cost visibility: Every API response includes the credit cost of that call, so agents can track spend in real time without a separate billing dashboard.
- Automatic rate limiting and retries: Orthogonal handles provider-level rate limits and retry logic transparently, so agents never need to implement backoff logic themselves.
- $10 free credits on sign-up: New Orthogonal accounts receive $10 in starting credits with no credit card required, enough for hundreds of lead lookups depending on the data provider.
Use Cases
- Target persona list building: A sales agent searches for 50 VP Engineering contacts at Series B SaaS companies in North America, returning a structured list ready for CRM import in under 30 seconds.
- Account-based marketing enrichment: A marketing agent queries a list of target accounts by company size and industry, then passes the results to a lead-enrichment step that appends verified emails before launching an email sequence.
- Investor outreach prospecting: A fundraising agent finds active seed-stage investors who have backed B2B SaaS companies in the last 12 months, using Orthogonal's data to build a cold outreach list without manual research.
- Competitive hiring intelligence: A talent agent locates engineers with specific skills at target competitor companies, giving a recruiter a vetted shortlist without browsing LinkedIn manually.
Install
orth skills add orthogonal/find-leadsRequirements
- Install the Orthogonal CLI: npm install -g @orth/cli
- Set your API key: export ORTHOGONAL_API_KEY=orth_live_your_key_here (get one free at orthogonal.com)
- OR add the MCP server to your agent config: { "mcpServers": { "orthogonal": { "url": "https://mcp.orth.sh" } } }
- $10 free credits are available on sign-up with no credit card required
Actions
Find Leads
Search for B2B prospects matching a target persona by job title, industry, company size, and location, returning a ranked list of matching contacts.
orth run orthogonal/find-leads /search -d '{
"job_title": "VP Engineering",
"industry": "SaaS",
"company_size": "51-200",
"location": "United States",
"limit": 25
}'job_title(string): Target job title(s) to filter by, e.g. 'CTO', 'VP Sales', 'Head of Marketing'.industry(string): Industry vertical, e.g. 'SaaS', 'FinTech', 'Healthcare', 'E-commerce'.company_size(string): Employee headcount range, e.g. '1-10', '11-50', '51-200', '201-1000', '1000+'.location(string): Geographic target such as a city, state, or country, e.g. 'San Francisco', 'United States', 'Europe'.keywords(string): Additional freetext keywords to narrow results, e.g. 'machine learning' or 'Series B'.limit(number): Maximum number of lead records to return.
Enrich Lead
Augment a known contact with verified email, direct phone number, social profiles, and full company metadata using Orthogonal's integrated data providers.
orth run orthogonal/find-leads /enrich -d '{
"name": "Jane Smith",
"company": "Acme Corp",
"domain": "acme.com",
"linkedin_url": "https://linkedin.com/in/janesmith"
}'name(string) — required: Full name of the person to enrich.company(string): Company name to narrow the person match when the name is common.domain(string): Company domain for high-precision email matching, e.g. 'acme.com'.linkedin_url(string): LinkedIn profile URL for the strongest possible person-matching confidence.
Export Lead List
Convert a batch of found leads into a structured JSON or CSV-ready array, with each record normalized across provider-specific field naming.
orth run orthogonal/find-leads /export -d '{
"leads": [
{ "name": "Jane Smith", "company": "Acme Corp" },
{ "name": "Bob Lee", "company": "Initech" }
],
"format": "json"
}'leads(array) — required: Array of lead objects (from a prior Find Leads call) to export and normalize.format(string): Output format: 'json' (default) or 'csv'.fields(array): Subset of fields to include in the export, e.g. ['name', 'email', 'company', 'job_title'].
How to Invoke
Installed via the Orthogonal CLI (`orth skills add orthogonal/find-leads`), which copies a SKILL.md file into the agent's skills directory. Alternatively, add `https://mcp.orth.sh` as an MCP server so the agent calls it as an MCP tool. The agent then calls `orth run orthogonal/find-leads /search` or `/enrich` with a JSON body containing search criteria.
Pricing
Pay-per-call credits with no monthly subscription. New accounts get $10 free credits with no credit card required. Credits are deducted per request at rates set by the underlying data provider. Enterprise tier available for high-volume workloads.
Strengths
- One Orthogonal key replaces 5+ individual B2B data subscriptions, saving 2-4 hours of API onboarding per provider.
- SKILL.md format installs in under 60 seconds and works across Claude Code, Cursor, Windsurf, and GitHub Copilot without any code changes.
- $10 free credits with no credit card means teams can validate the skill in a real pipeline before committing to paid usage.
- MCP server at mcp.orth.sh means Claude Desktop users can use the skill with a single config line, no CLI required.
- Per-call cost included in every API response makes it easy to budget agent pipelines without surprises.
Weaknesses
- The platform launched in January 2026 and has fewer than 12 months of production track record, so reliability data at scale is limited.
- Pay-per-call pricing is less predictable than a flat monthly seat license for teams running high-volume daily prospecting campaigns.
- The find-leads skill depends on Orthogonal's third-party data partnerships, so data freshness and accuracy vary by provider and may not match a direct Apollo.io or People Data Labs subscription.
Frequently Asked Questions
What is Orthogonal Find Leads and what does it do?
Orthogonal Find Leads is an agent skill built by Orthogonal, a YC W26 company that provides a unified API gateway for AI agents. The skill teaches any compatible agent how to discover B2B prospects by accepting search criteria like job title, industry, company size, and location, then querying a catalog of over 30 data providers including Apollo.io, People Data Labs, ContactOut, and Ocean.io. It returns a ranked list of matching contacts with names, companies, job titles, and LinkedIn URLs, plus verified emails and phone numbers where available. The skill is distributed as a SKILL.md file, a plain-text markdown format that major agent platforms read natively, meaning no binary installation or SDK is required. It also supports access via the Orthogonal MCP server at mcp.orth.sh for clients like Claude Desktop. Orthogonal handles all provider authentication, rate limiting, and retry logic centrally, so the agent only needs a single ORTHOGONAL_API_KEY to access every data source.
How do I install and set up Orthogonal Find Leads?
Installation takes two steps. First, install the Orthogonal CLI by running `npm install -g @orth/cli` in a terminal with Node.js 18 or higher. Second, add the skill to your agent's directory by running `orth skills add orthogonal/find-leads`, which copies the SKILL.md file into the appropriate folder for your agent platform (Claude Code, Cursor, Windsurf, GitHub Copilot, or Codex CLI). You must also set your API key as an environment variable: `export ORTHOGONAL_API_KEY=orth_live_your_key_here`. New accounts get $10 in free credits at orthogonal.com with no credit card required. If you prefer the MCP approach, add `{ "mcpServers": { "orthogonal": { "url": "https://mcp.orth.sh" } } }` to your agent's MCP config instead of using the CLI. After installation, your agent can call `orth run orthogonal/find-leads /search` with a JSON body containing your search criteria.
Which agents and LLMs support Orthogonal Find Leads?
Any agent that reads SKILL.md files can use this skill, which as of June 2026 includes Claude Code, Cursor, Windsurf, GitHub Copilot, Codex CLI, OpenClaw, and Gemini CLI. Claude Desktop and other MCP-compatible clients can connect via the Orthogonal MCP server at mcp.orth.sh without any CLI installation. The underlying Orthogonal REST API is language-agnostic, so custom agents built with any LLM (Claude, GPT-4, Gemini, Llama) can call it directly using the API key. The SKILL.md format is a plain-text markdown spec with no runtime dependency, so adding support for new agent platforms requires no code change on the skill's side. Orthogonal's compatibility list has grown from 3 to 8 platforms since the product launched in January 2026. The skill does not require a specific LLM provider and works equally well whether the orchestrating model is Claude, GPT-4o, or an open-source alternative.
How much does Orthogonal Find Leads cost?
Orthogonal uses a pay-per-call credit model with no monthly subscription or minimum spend. New accounts receive $10 in free starting credits, which is enough for a meaningful number of test queries depending on which data providers are queried for each request. Each API response includes the credit cost of that specific call, so agents can track per-call spend in real time without a separate billing dashboard. Credits can be topped up manually at any time, or users can enable auto top-up (currently in beta) to keep a credit balance automatically. An enterprise tier is available for teams with high-volume agent workloads and includes custom credit packages and dedicated support. There is no free tier with unlimited usage; after the $10 starter credits are exhausted, users pay for each call.
Is Orthogonal Find Leads open source?
The SKILL.md files for the Orthogonal skills catalog, including find-leads, are maintained in the public GitHub repository at github.com/orthogonal-sh/skills under an open-source license, so you can inspect, fork, and modify the skill definition itself. The Orthogonal platform (the API gateway, billing layer, MCP server, and data provider integrations) is a proprietary commercial service. This means you can self-host the SKILL.md file for free, but queries routed through Orthogonal's infrastructure require a paid API key. Orthogonal was founded by engineers from Coinbase and Google and is backed by Y Combinator W26, and the platform is designed to remain a managed service rather than a self-hostable alternative. The skill format itself (SKILL.md) is an open standard adopted by multiple agent ecosystems and is not locked to Orthogonal's platform.
What are the best alternatives to Orthogonal Find Leads?
The closest alternatives are Apollo.io's direct API and People Data Labs, both of which offer B2B contact search with similar data coverage but require individual account setup, API key management, and separate billing relationships. Clay is another option that orchestrates multiple data providers for lead enrichment in a no-code workflow builder, though it is priced per seat rather than per call. Hunter.io covers email discovery specifically and is a good pick when verified email is the only data point needed. The Orthogonal Lead Enrichment skill (also in the Orthogonal catalog) handles enrichment of known contacts but does not do cold discovery. For teams that want full control over data provider routing and don't mind managing multiple accounts, direct Apollo.io or PDL access gives more configuration options. Pick Orthogonal Find Leads when a single API key and low operational overhead matter more than per-provider customization.
Who is Orthogonal Find Leads best for?
The skill is best for sales engineers, GTM engineers, and developer-founders who are building agent-powered outbound pipelines and need B2B contact data without setting up 3-5 separate data provider accounts. It is particularly well suited for early-stage teams doing initial pipeline validation, since the $10 free credits let them test a real workflow before committing to paid data spend. AI developers prototyping lead-generation agents will benefit from the fast setup (under 5 minutes from zero to a running query). It is NOT the best fit for large enterprise sales teams with existing Apollo.io or ZoomInfo contracts, since those teams already have per-seat pricing that would likely be cheaper at high volume. It is also not ideal for teams that need proprietary data signals like intent data, technographics, or hiring signals, since Orthogonal's catalog focuses on contact and firmographic data rather than behavioral signals.
How does Orthogonal Find Leads compare to Apollo.io's agent skill in 2026?
Apollo.io's agent skill gives direct access to its 230 million contact database with native intent scoring and CRM sync features, but requires an active Apollo.io subscription (starting around $49 per user per month) and a separate API key. Orthogonal Find Leads queries Apollo.io as one of 30+ data sources under a single Orthogonal key, so you pay per call rather than per seat, but you lose Apollo-specific features like intent signals and email sequences. For teams already paying for Apollo.io seats, using Apollo's skill directly gives more data depth and lower per-record cost at high volume. For teams without an Apollo.io contract, Orthogonal Find Leads is faster to set up, cheaper to start, and gives access to multiple providers rather than just one. The SKILL.md format used by Orthogonal installs across more agent platforms than Apollo's dedicated skill, which supports a narrower set of clients. Pick Apollo.io directly for production outbound at scale; pick Orthogonal Find Leads for agent prototyping, multi-source discovery, or teams that want one key to rule all their data providers.