# Plith MCP server

Source: https://glimind.com/server/mcp-registry%2Fai.plith%2Fplith
Registry id: `mcp-registry/ai.plith/plith`
Status: live (checked 2026-10-26T18:10:12.726Z)

## Verdict

Plith MCP server answered 99.95% of Glimind's liveness checks over 30 days, better than 36% of MCP servers, with 3696 ms median handshake and 7 outages in 90 days. Its agent-readiness grade is A (90/100) across 15 tools, costing an agent about 7,874 tokens to load. Checked every few minutes; no tool is ever called.

## Measurements (30 days)

| Metric | Value | Better than |
|---|---|---|
| Uptime, 30 days | 99.95% | 36% of MCP servers |
| Median handshake latency | 3696 ms | 1% of MCP servers |
| p95 handshake latency | 8522 ms | — |
| Checks in 30 days | 4,932 | — |
| Outages, 90 days | 7 | — |
| Median recovery | 7 min | — |
| Agent-readiness score | 90/100 (A) | 69% of MCP servers |
| Tools | 15 | — |
| Tool-list size for an agent | ~7,874 tokens | 33% of MCP servers |
| Days observed | 29 | — |

## Install

```json
{
  "mcpServers": {
    "plith-mcp-server": {
      "type": "http",
      "url": "https://plith.ai/api/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http plith-mcp-server https://plith.ai/api/mcp
```

## Tools (15)

- `burnrate_budget`: Get today's tracked LLM spend, per-model breakdown, projection, and budget alerts. Free — no credits charged.
- `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 bud
- `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. Retur
- `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 ti
- `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.
- `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.
- `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 cre
- `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, resour
- `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, su
- `pitfalldb_report`: Report an agent failure. PII-scrubbed before storage. Linked to existing pitfalls if similar. Free — no credits charged.
- `qualitygate_validate`: After your agent generates output, validate it against your rules before shipping. Runs deterministic checks (regex, JSON schema, syntax) plus optional LLM-powe
- `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 
- `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 
- `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 
- `rigor_workflows`: List and search Rigor workflows for your organization, with filtering and pagination. Returns status, progress, capacity usage, and available actions per workfl

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.