Skip to main content
The MCP server ships with Agent Skills — pre-built workflow instructions that teach AI agents how to combine Databar tools for common tasks. Skills follow the open SKILL.md standard and work across 27+ agents including Claude, Cursor, Codex, Gemini CLI, OpenClaw, Windsurf, and GitHub Copilot.

​
Available skills

Single Enrichment

Look up a person, company, email, or phone number using the best matching enrichment

Table-Driven Enrichment

Create a table, insert rows, attach an enrichment, run it, and get a sharable link

Waterfall Enrichment

Try multiple data providers in sequence to maximize success rate

Bulk Enrichment

Enrich a list of up to 100 records in a single operation with inline results

​
How skills work

Without skills, you have to guide the AI step-by-step: “search for an enrichment, then get details, then run it…” With skills, you just say “find the email for John Smith at Google” and the agent knows the full workflow automatically. Skills use a three-phase loading model to stay efficient:
PhaseWhat loadsToken cost
DiscoveryName and description only~100 tokens per skill
ActivationFull instructions when the task matchesUnder 5,000 tokens
ExecutionAgent follows the workflowZero additional overhead
Skills are loaded on demand — they don’t consume context until the agent decides they’re relevant to your request.

​
Skill details

​
Single Enrichment (databar-enrichment)

Triggers when the user asks to look up, find, or enrich a single data point — a person, company, email, phone number, or domain. Workflow:
  1. Extract the user’s intent and entity type
  2. search_enrichments to find the right provider
  3. get_enrichment_details to check parameters and pricing
  4. Confirm cost with the user
  5. run_enrichment and present results
Example prompt: “Get me the LinkedIn profile for Sarah Chen at Stripe”

​
Table-Driven Enrichment (databar-table-enrichment)

Triggers when the user wants to enrich a dataset at scale using Databar tables — create a table, add rows, run enrichments, and get a link to view results. Workflow:
  1. Parse the user’s data (CSV, JSON, or plain text)
  2. create_table and create_rows (up to 100 per batch)
  3. search_enrichments to find the right provider
  4. add_table_enrichment with column mapping
  5. run_table_enrichment on all rows
  6. Provide a link: https://databar.ai/table/{uuid}
Example prompt: “Here are 30 leads with name and company. Create a table and find their emails.”

​
Waterfall Enrichment (databar-waterfall)

Triggers when the user wants to maximize success rate by trying multiple providers, or explicitly mentions “waterfall”. Workflow:
  1. search_waterfalls to find available waterfalls
  2. Pick the best match based on the user’s goal
  3. run_waterfall (single) or run_bulk_waterfall (multiple inputs)
  4. Optionally chain with email verification
Example prompt: “Find the email for David Kim at Databar using a waterfall”

​
Bulk Enrichment (databar-bulk-enrichment)

Triggers when the user provides a list of items to enrich and wants quick inline results without creating a table. Workflow:
  1. Parse the user’s list (CSV, JSON, or plain text)
  2. search_enrichments to find the right provider
  3. Estimate cost: item_count x price_per_enrichment
  4. Confirm with the user
  5. run_bulk_enrichment (max 100 items per request)
  6. Format results as a markdown table
Example prompt: “Verify these emails: alice@google.com, bob@fake.xyz, carol@stripe.com”
Bulk enrichment supports up to 100 items per request. For larger datasets, the agent will suggest using the table-driven approach instead.

​
Installing skills

Skills are included in the skills/ folder of the GitHub repo. To use them:
Copy the skill folders into your Claude skills directory:
git clone https://github.com/databar-ai/databar-mcp-server.git
cp -r databar-mcp-server/skills/* ~/.claude/skills/
Claude will automatically discover and activate the skills when relevant.