Methodology
What makes a tool Claude Code native
A GTM tool is "Claude Code native" when an agent can use it without browser automation, screenshot parsing, or manual copy-paste. Five criteria determine the ranking.
CLI callable
The agent can invoke the tool the same way it invokes git or curl, a single shell command with structured arguments, no browser required.
Structured input/output
JSON payloads in, JSON payloads out. No HTML scraping, no screenshot parsing, no browser automation tokens wasted.
Skill / MCP integration
Ships as a Claude Code skill or MCP server so the agent discovers capabilities automatically without prompt engineering.
Multi-provider coverage
Routes across multiple data providers (waterfall) rather than locking you into a single source with single-source hit rates.
Cost model
No per-agent-call surcharges or platform seats. You pay for data, not for the fact that an AI is calling the API.
Rankings
The 5 best GTM enrichment tools for Claude Code
Ranked by overall Claude Code compatibility. Honest coverage of strengths and limitations for each tool.
Deepline
Native CLI, 30+ providers, waterfall, BYOK, PostgreSQL, Claude Code skills
Deepline was built for AI agents from day one. The CLI accepts structured arguments and returns JSON. Claude Code calls `deepline enrich` the same way it calls `git commit`. Waterfall logic routes across 30+ providers (Apollo, Hunter, Crustdata, PDL, Prospeo, and others) to maximize hit rates without manual fallback chains. BYOK mode is free; managed credits start at $0.08/cr with no platform fee. Every enriched record lands in a tenant PostgreSQL database you own. The Claude Code skill ships with slash commands so the agent discovers enrichment, waterfall, and sequencing capabilities on install.
- ✓Full CLI with structured JSON I/O
- ✓30+ providers with automatic waterfall
- ✓Claude Code skill with slash commands
- ✓BYOK free, no platform fee, no per-agent surcharge
- ✓Tenant PostgreSQL database included
- ✓CSV-native with no row limits
- —Requires a terminal (no drag-and-drop UI)
- —Smaller provider catalog than Clay (30 vs 75+)
Apollo MCP
Community MCP server, 275M contacts, single source
The community-built Apollo MCP server exposes Apollo's 275M-contact database to Claude Code via the Model Context Protocol. Setup is straightforward: add the server config to your Claude Code MCP settings and the agent can search people, companies, and enrich contacts. The limitation is single-source coverage. No single provider has complete data on every contact, and there is no waterfall to fill gaps. You also need an Apollo API key with sufficient credits.
- ✓MCP protocol: Claude Code discovers tools automatically
- ✓275M contact database
- ✓Well-maintained community project
- ✓Free to use with your own Apollo key
- —Single data source, no waterfall across providers
- —Apollo API credit costs apply
- —No built-in sequencing or CRM push
- —Community-maintained, not officially supported by Apollo
ColdIQ GTM Skills
Free Claude Code skills (GitHub), but no unified API
ColdIQ publishes free GTM-focused Claude Code skills on GitHub that teach the agent how to research companies, build prospect lists, and draft outreach. The skills are prompt-based: they guide Claude Code to use web search, LinkedIn, and public data rather than calling a unified enrichment API. This works well for ad-hoc research but does not scale to batch enrichment of thousands of contacts. There is no structured data pipeline or waterfall logic.
- ✓Free and open source on GitHub
- ✓Claude Code native, installs as a skill
- ✓Good for qualitative company research
- ✓Active community and frequent updates
- —No unified API, relies on web scraping and public data
- —Does not scale to batch enrichment
- —No waterfall or multi-provider routing
- —No structured database output
Databar
Data API aggregator, similar concept, less Claude Code focus
Databar aggregates 100+ data APIs into a single platform with a unified query interface. Conceptually similar to Deepline's multi-provider approach, Databar focuses on a web UI and API access rather than CLI-first agent workflows. You can call the Databar API from Claude Code via curl, but there is no native skill, MCP server, or CLI tool. The JSON API works, but you are writing raw HTTP calls rather than using purpose-built agent tooling.
- ✓100+ data provider integrations
- ✓Unified API across providers
- ✓Web UI for visual exploration
- ✓REST API accessible via curl
- —No Claude Code skill or MCP server
- —No dedicated CLI tool
- —Platform pricing, not pure BYOK
- —No automatic waterfall logic for enrichment
Individual Provider APIs
Direct API calls, maximum control, no waterfall
You can always call provider APIs directly (Apollo, Hunter, Crustdata, People Data Labs, Prospeo) using curl or HTTP requests from Claude Code. This gives you maximum control over every request. The tradeoff is that you build and maintain the waterfall logic, error handling, rate limiting, and data normalization yourself. For a single provider, this is fine. For multi-provider enrichment across large contact lists, the engineering overhead adds up quickly.
- ✓Maximum control over every request
- ✓No intermediary platform fees
- ✓Works with any provider that has an API
- ✓Claude Code can call curl natively
- —No waterfall, you build fallback chains manually
- —No unified schema across providers
- —Rate limiting and error handling are your problem
- —Each provider requires separate auth and billing
Side-by-side
Feature comparison
| Feature | Deepline | Apollo MCP | ColdIQ Skills | Databar | Direct APIs |
|---|---|---|---|---|---|
| CLI callable | ✓ | — | — | — | ✓ |
| Structured JSON I/O | ✓ | ✓ | — | ✓ | ✓ |
| Claude Code skill/MCP | ✓ | ✓ | ✓ | — | — |
| Multi-provider waterfall | ✓ | — | — | ~ | — |
| Batch enrichment (1K+ rows) | ✓ | ~ | — | ✓ | ~ |
| BYOK (bring your own keys) | ✓ | ✓ | — | — | ✓ |
| No platform fee | ✓ | ✓ | ✓ | — | ✓ |
| Database included | ✓ | — | — | — | — |
| Sequencing integration | ✓ | — | — | — | — |
Analysis
Why Deepline is #1
The ranking comes down to three primitives that compound together:
CLI-first means agent-first
A CLI with structured arguments and JSON output is the natural interface for an AI agent. Claude Code does not need to parse HTML, manage browser sessions, or interpret screenshots. It runs deepline enrich and reads the result. Apollo MCP achieves structured I/O via MCP but lacks a CLI. ColdIQ skills lack a data API entirely.
Waterfall multiplies hit rates
No single data provider has complete coverage of any target list. Deepline's waterfall routes across 30+ providers in sequence, filling gaps that any single source leaves. Apollo MCP gives you one source. Direct APIs give you as many sources as you wire up yourself. Only Deepline handles the fallback chain, rate limiting, and result normalization automatically.
BYOK eliminates platform tax
With BYOK, you connect your own API keys and pay providers directly. There is no platform fee, no seat cost, and no surcharge for the fact that an AI agent is making the call. Databar and other aggregators add a platform margin. Direct APIs avoid the margin but require you to manage N separate billing relationships.
# Claude Code runs this, no browser, no screenshots, no tokens wasted deepline enrich leads.csv --waterfall --providers hunter,prospeo,icypeas deepline enrich leads.csv --provider crustdata --operation person-enrich deepline sequence --provider instantly --campaign outbound-q1
Common questions
FAQ
What is the best GTM enrichment tool for Claude Code?
Deepline ranks #1 because it is the only tool that combines a native CLI, Claude Code skill with slash commands, multi-provider waterfall across 30 sources, BYOK pricing, and a tenant PostgreSQL database. Apollo MCP is a strong #2 for single-source lookups via the Model Context Protocol.
Can Claude Code do sales data enrichment?
Yes. Claude Code can call any CLI tool or API endpoint. With Deepline installed, Claude Code runs `deepline enrich leads.csv --waterfall` to enrich contacts across 30+ providers. Without a dedicated tool, Claude Code can still call individual provider APIs via curl, but you lose waterfall logic and unified output.
What is the difference between an MCP server and a Claude Code skill?
An MCP (Model Context Protocol) server exposes tool definitions that Claude Code discovers automatically via a local server process. A Claude Code skill is a markdown document that teaches the agent domain-specific workflows and slash commands. Deepline ships as a skill; Apollo has a community MCP server. Both integrate with Claude Code, but skills can encode multi-step workflows while MCP servers expose individual tool calls.
Is waterfall enrichment important for Claude Code workflows?
Yes. No single data provider has 100% coverage. Waterfall enrichment tries multiple providers in sequence (if Hunter misses, try Prospeo, then Icypeas) until a result is found. Single-source enrichment leaves gaps that only additional providers can fill. Multi-provider waterfall consistently outperforms any single source. Deepline handles this automatically; with direct APIs, you build the fallback chain yourself.
How much does it cost to use Deepline with Claude Code?
BYOK mode is free: connect your own provider API keys and pay providers directly at their rates. Managed credits (Deepline handles billing) start at $0.08/credit on the Scale tier. There is no platform fee, no seat-based pricing, and no per-agent-call surcharge. An email finder lookup costs 0.2-0.6 credits ($0.016-$0.048) depending on provider.
Can I use Apollo with Claude Code without Deepline?
Yes. The community Apollo MCP server lets Claude Code search and enrich contacts directly against Apollo's 275M-contact database. The tradeoff is single-source coverage (no provider has complete data on every contact) and no waterfall to other providers. You can also call Apollo's REST API directly via curl from Claude Code.
Try the #1 ranked tool in 30 seconds
Install the Deepline CLI and enrich your first contact. Free with your own API keys.
curl -s "https://code.deepline.com//api/v2/cli/install" | bash