QUICKSTART

Get started with Plith

Five tools for AI agents: deduplication, cost estimation, output validation, behavioral governance, and cross-org failure learning. Pick your integration path below.

Get your API key

Keys are free — no signup form, no dashboard. Just one API call. Both fields are optional but recommended.

curl -X POST https://plith.ai/api/keys \
  -H "Content-Type: application/json" \
  -d '{"email": "[email protected]", "name": "Your Org"}'

{
  "org_id": "org_abc123",
  "key": "plth_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
  "prefix": "plth_xxxxxx",
  "message": "Store this key securely — it will not be shown again."
}

⚠The key is returned once and cannot be retrieved again — save it immediately.

• Free tier: 1,000 credits/month auto-granted on your first API call — no card required.

• Rate limit: 3 keys per IP per 24 hours.

Choose your path

Path 1 — MCP Connection

One config block. Works with Claude Desktop, Claude Code, and any MCP client.

Path 2 — REST API

Direct HTTP. Works with any language or framework.

Add Plith to your MCP client config. Plith exposes 14 MCP tools using product_action naming — e.g., dedupq_check, burnrate_estimate. Arguments are passed directly, no action/params nesting needed.

Step 1 — Get an API key

curl -X POST https://plith.ai/api/keys \
  -H "Content-Type: application/json" \
  -d '{"email": "[email protected]"}'

# Response — store the key securely, it is shown once 
{
  "org_id": "org_abc123",
  "key": "plth_xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
  "prefix": "plth_xxxxxx",
  "message": "Store this key securely — it will not be shown again."
}

⚠The key is shown once and never stored in plaintext. Copy it now.

Step 2 — Add to your MCP client config

For Claude Desktop, edit ~/Library/Application Support/Claude/claude_desktop_config.json. For Claude Code, run claude mcp add or edit .mcp.json in your project root.

{
  "mcpServers": {
    "plith": {
      "url": "https://plith.ai/api/mcp",
      "headers": {
        "x-api-key": "YOUR_API_KEY"
      }
    }
  }
}

✓Restart your MCP client. The agent now has access to 14 Plith MCP tools: dedupq_check, burnrate_estimate, qualitygate_validate, guardrail_check, pitfalldb_query, and more.

Example MCP calls

The tool name uses underscore naming (e.g., dedupq_check); arguments are passed directly as the tool's input parameters.

# dedupq_check — check for duplicate tasks
{
  "name": "dedupq_check",
  "arguments": {
    "content": "Summarize the Q3 earnings report",
    "task_id": "task_789"
  }
}

# burnrate_estimate — estimate LLM cost
{
  "name": "burnrate_estimate",
  "arguments": {
    "plan": [
      {"step": 1, "provider": "anthropic", "model": "claude-sonnet-4-6",
       "estimated_input_tokens": 2000, "estimated_output_tokens": 500}
    ]
  }
}

# Legacy: flat names (dedupq, burnrate, etc.) and "plith" umbrella
# still work for backward compatibility
{
  "name": "plith",
  "arguments": { "action": "dedupq.check", "params": { ... } }
}

Authentication

Pass your API key in the x-api-key header on every request. Only /api/keys is unauthenticated.

curl https://plith.ai/api/dedupq/check \
  -H "x-api-key: plth_xxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{...}'

All endpoints

All product endpoints require x-api-key header except /api/keys.

MethodEndpointCost

POST

/api/keysCreate org + API key. Body: { email?, name? }

FREE

GET

/api/keys/verifyVerify an API key is valid

FREE

POST

/api/guardrail/policiesCreate a guardrail policy. Body: { name, rules }

FREE

POST

/api/dedupq/checkCheck for duplicate or semantically similar cached tasks.

1 credit

POST

/api/dedupq/completeMark a task complete and store its result in the dedup cache.

2 credits

POST

/api/burnrate/estimateEstimate LLM cost for a multi-step agent plan.

1 credit

POST

/api/burnrate/trackRecord actual LLM spend for a completed task.

FREE

POST

/api/burnrate/optimizeGet cheaper model substitutions for a plan given a target budget.

1 credit

GET

/api/burnrate/budgetGet current period spend, budget, and burn rate.

FREE

POST

/api/qualitygate/validateValidate agent output against configured quality rules.

1-8 / check

GET

/api/qualitygate/trendsGet validation pass/fail trends over time.

FREE

POST

/api/guardrail/checkCheck a proposed action against behavioral policies.

1 credit

GET

/api/guardrail/policiesList your active guardrail policies.

FREE

POST

/api/pitfalldb/queryQuery known failure patterns for a task type.

2 credits

POST

/api/pitfalldb/reportReport a new agent failure. Contributes to the cross-org database.

FREE

GET

/api/pitfalldb/statsDatabase stats: total pitfalls, top task types, recent additions.

FREE

GET

/api/billing/balanceGet credit balance and plan details.

FREE

POST

/api/billing/checkoutPurchase credits. Amounts: 10, 25, or 100 USD.

FREE

Free tier: 1,000 credits/month

No card required. Create a key and start building.

Full API ReferenceOpenAPIAuthentication →