Plith is an MCP server with 15 tools an agent can call, among them burnrate_budget, burnrate_estimate, burnrate_optimize. It answers at https://plith.ai/api/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 4 September 2026; the last check, on 17 October 2026, succeeded.
AI agent infrastructure: dedup, cost prediction, validation, governance, failure intelligence.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
burnrate_budget | Get today's tracked LLM spend, per-model breakdown, projection, and budget alerts. Free — no credits charged. Inputs: daily_limit |
burnrate_estimate | Before executing a multi-step agent plan, estimate the total LLM cost. Returns per-step breakdown and optimization suggestions. If the estimate exceeds your budget, pipe the same plan into burnrate_optimize. Costs 1 credit. Inputs: plan |
burnrate_optimize | Get a cheaper equivalent plan by substituting models with lower-cost alternatives. Call after burnrate_estimate if the estimated cost exceeds your budget. Returns the optimized plan with substituted models, new per-step costs, total savings Inputs: plan, target_budget |
burnrate_track | Log the actual cost of an LLM call after execution. Call this after every LLM request to build calibration data that improves burnrate_estimate accuracy over time. Free — no credits charged. Returns the recorded cost entry with computed mar Inputs: provider, model, input_tokens, output_tokens, task_id, cache_read_tokens |
dedupq_check | Before executing any LLM task, check if an identical or semantically similar task has already been completed. Returns cached result on hit, saving one LLM call. On a miss, execute your task and call dedupq_complete to cache the result for f Inputs: content, task_id, hash_only, similarity_threshold |
dedupq_complete | After executing a task, store the result so future identical or similar tasks return a cache hit via dedupq_check. Costs 2 credits. Inputs: content, result, task_id, hash_only |
guardrail_check | Evaluate a proposed agent action against your governance policies. Returns allow or deny with the matched policy reason. Requires at least one active policy created via guardrail_create_policy. Deterministic rule evaluation — no LLM. Costs Inputs: agent_id, proposed_action |
guardrail_create_policy | Create a persistent governance policy that guardrail_check evaluates on every subsequent call. Define rules using and/or/not operators over action types, resource patterns, and budget thresholds. Call this before using guardrail_check — che Inputs: name, description, rules, action_types, priority |
pitfalldb_query | Check for known failure patterns before executing a task type. Returns pitfalls with severity, fix suggestions, and confidence scores. After your agent runs, submit failures via pitfalldb_report so others benefit. Costs 2 credits. Inputs: task_type, task_description, filters |
pitfalldb_report | Report an agent failure. PII-scrubbed before storage. Linked to existing pitfalls if similar. Free — no credits charged. Inputs: task_type, task_description, failure |
qualitygate_validate | After your agent generates output, validate it against your rules before shipping. Runs deterministic checks (regex, JSON schema, syntax) plus optional LLM-powered tone and factual analysis. Returns a structured verdict (pass, warn, or fail Inputs: output, directives, schema, language, check_types, override |
rigor_execute | Execute a structured workflow end-to-end. Call rigor_plan first (free) to preview the step sequence and cost estimate before committing credits. Classifies the task, selects the optimal tool sequence, and executes each step with the right L Inputs: task_description, task_type, delivery, preferences, context |
rigor_plan | Before executing a complex task, get a structured workflow plan with per-step cost estimates. Classifies your task, selects the optimal framework sequence, and returns the full plan without executing anything. The response's allowed_modes t Inputs: task_description, task_type, preferences |
rigor_status | Check the status of a running or completed Rigor workflow. Returns progress, step results, and the full deliverable when complete. Use after rigor_execute with polling delivery to retrieve results. Inputs: workflow_id |
rigor_workflows | List and search Rigor workflows for your organization, with filtering and pagination. Returns status, progress, capacity usage, and available actions per workflow. Use to monitor workflow state, understand concurrent limit usage, identify s Inputs: status, task_type, q, folder_id, created_after, created_before |
Every block below points at https://plith.ai/api/mcp. Pick your client and copy.
claude mcp add --transport http plith https://plith.ai/api/mcp
{
"mcpServers": {
"plith": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://plith.ai/api/mcp"]
}
}
}{
"mcpServers": {
"plith": {
"url": "https://plith.ai/api/mcp"
}
}
}{
"servers": {
"plith": {
"type": "http",
"url": "https://plith.ai/api/mcp"
}
}
}{
"context_servers": {
"plith": {
"url": "https://plith.ai/api/mcp"
}
}
}{
"mcpServers": {
"plith": {
"serverUrl": "https://plith.ai/api/mcp"
}
}
}{
"mcpServers": {
"plith": {
"url": "https://plith.ai/api/mcp"
}
}
}name: Plith
version: 0.0.1
schema: v1
mcpServers:
- name: Plith
type: streamable-http
url: https://plith.ai/api/mcp{
"mcpServers": {
"plith": {
"httpUrl": "https://plith.ai/api/mcp"
}
}
}{
"mcpServers": {
"plith": {
"type": "http",
"url": "https://plith.ai/api/mcp"
}
}
}{
"mcpServers": {
"plith": {
"url": "https://plith.ai/api/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fplith.ai%2Fapi%2Fmcp&type=streamable_http&id=plith&name=Plith
It answered our last check on 17 October 2026 in 249 ms. Over 10 checks since 4 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by plith.ai and served from plith.ai, the vendor's own domain: https://plith.ai/api/mcp.
15, as returned by the server's own tools/list on 8 September 2026: burnrate_budget, burnrate_estimate, burnrate_optimize, burnrate_track, dedupq_check, dedupq_complete, guardrail_check, guardrail_create_policy, and 7 more.
It answered our last check on 17 October 2026 in 249 ms. Over 10 checks since 4 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://plith.ai/api/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: ai.plith. Endpoint host: plith.ai. ARD identifier: urn:air:ai.plith:mcp:plith.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.