Skip to content

plith MCP server

ai.plith/plithplith.aistreamable-httpv1.0.0Scanned

AI agent infrastructure: dedup, cost prediction, validation, governance, failure intelligence.

15 tools: 12 change things and 3 only read.

Tools: 0 delete, 0 irreversible, 12 write, 3 read.
  • Reads private data · 1
  • Reads text others write · 7
  • Can send data out · 1
  • 4 findings

Tools listed without sign-in. Remote posture

Anlyon alternative

12 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon Radar does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

What the plith MCP server can do

The plith MCP server is published by plith.ai, a domain the MCP Registry verified. It has 15 tools. It can create or change data (12 tools: dedupq_check, dedupq_complete, burnrate_estimate, burnrate_track and 8 more), but cannot delete data. 3 tools only read.

1 tool reads private data (rigor_workflows); 7 tools bring in text other people can write (dedupq_check, dedupq_complete, qualitygate_validate and 4 more); 1 tool can send data out of your system (rigor_execute). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.

The fixed checks matched 4 findings (annotation-conflict). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 10, 2026, version 1.0.0.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

15 tools

Changes things 12Claude Code: ask
  • burnrate_estimateBefore executing a multi-step agent plan, estimate the total LLM cost.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Estimate LLM cost for a plan
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • burnrate_optimizeGet a cheaper equivalent plan by substituting models with lower-cost alternatives.1 finding

    Why it is in this group

    • The description's first verb is "get": a word for reading.
    • The server marks it as not read-only (readOnlyHint: false).

    Findings

    • Warn

      The server marks "burnrate_optimize" as not read-only (readOnlyHint: false), and its words say it reads.

      Matched text

      annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "get": a word for reading.

      What this check looks for
    Description, as the server wrote it
    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, and whether the target_budget is met. Optionally set target_budget to constrain the optimization. Costs 1 credit.

    Annotations the server declares

    • title: Optimize plan for lower cost
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • burnrate_trackLog the actual cost of an LLM call after execution.1 finding

    Why it is in this group

    • The description's first verb is "log": a word for reading.
    • The server marks it as not read-only (readOnlyHint: false).

    Findings

    • Warn

      The server marks "burnrate_track" as not read-only (readOnlyHint: false), and its words say it reads.

      Matched text

      annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "log": a word for reading.

      What this check looks for
    Description, as the server wrote it
    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 margin versus the prior estimate when one exists for this model and token range.

    Annotations the server declares

    • title: Record actual LLM spend
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • dedupq_checkBefore executing any LLM task, check if an identical or semantically similar task has already been completed.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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 future hits. Costs 1 credit.

    Annotations the server declares

    • title: Check for duplicate tasks
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • dedupq_completeAfter executing a task, store the result so future identical or similar tasks return a cache hit via dedupq_check.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    After executing a task, store the result so future identical or similar tasks return a cache hit via dedupq_check. Costs 2 credits.

    Annotations the server declares

    • title: Store completed task result
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • guardrail_checkEvaluate a proposed agent action against your governance policies.No findings

    Why it is in this group

    • The description's first verb is "evaluate": a word for a change.
    Description, as the server wrote it
    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 1 credit.

    Annotations the server declares

    • title: Check action against policies
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • guardrail_create_policyCreate a persistent governance policy that guardrail_check evaluates on every subsequent call.No findings

    Why it is in this group

    • The name "guardrail_create_policy" says "create": a word for a change.
    Description, as the server wrote it
    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 — checks require at least one active policy. Policies persist until explicitly deleted. Duplicate policy names return an error. Returns the created policy with its ID and active status.

    Annotations the server declares

    • title: Create governance policy
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: false
  • pitfalldb_queryCheck for known failure patterns before executing a task type.Reads text others write1 finding

    Why it is in this group

    • The name "pitfalldb_query" says "query": a word for reading.
    • The server marks it as not read-only (readOnlyHint: false).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Warn

      The server marks "pitfalldb_query" as not read-only (readOnlyHint: false), and its words say it reads.

      Matched text

      annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "pitfalldb_query" says "query": a word for reading.

      What this check looks for
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Query known failure patterns
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • pitfalldb_reportReport an agent failure.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    Report an agent failure. PII-scrubbed before storage. Linked to existing pitfalls if similar. Free — no credits charged.

    Annotations the server declares

    • title: Report an agent failure
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • qualitygate_validateAfter your agent generates output, validate it against your rules before shipping.Reads text others write1 finding

    Why it is in this group

    • The name "qualitygate_validate" says "validate": a word for reading.
    • The server marks it as not read-only (readOnlyHint: false).

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Warn

      The server marks "qualitygate_validate" as not read-only (readOnlyHint: false), and its words say it reads.

      Matched text

      annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "qualitygate_validate" says "validate": a word for reading.

      What this check looks for
    Description, as the server wrote it
    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) with a 0-100 score and per-check issue details. Use qualitygate_trends to spot recurring failure patterns over time. Variable cost: 1 credit per deterministic check, 8 credits per LLM check.

    Annotations the server declares

    • title: Validate agent output
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • rigor_executeExecute a structured workflow end-to-end.Reads text others writeCan send data outNo findings

    Why it is in this group

    • The name "rigor_execute" says "execute": a word for a change.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    • outboundThe input takes a URL (input.delivery.webhook_url): a request to a URL can carry data to whoever runs it.
    Description, as the server wrote it
    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 LLM model. Returns a complete deliverable — solution designs, competitive analyses, governance documents, and more. Supports SSE streaming for real-time progress, webhook callback, or polling. For atomic work — classification, scoring, ranking, entity extraction, query parsing — set preferences.execution to 'direct' and declare preferences.output_contract to get validated JSON records from a single call, routed to the cheapest model that holds the schema.

    Annotations the server declares

    • title: Execute a Rigor workflow
    • readOnlyHint: false
    • destructiveHint: false
    • idempotentHint: false
    • openWorldHint: true
  • rigor_planBefore executing a complex task, get a structured workflow plan with per-step cost estimates.Reads text others writeNo findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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 tells you whether this plan is eligible for direct execution. Free — no credits charged.

    Annotations the server declares

    • title: Plan a Rigor workflow
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
Only reads 3Show 3 read-only tools
  • burnrate_budgetGet today's tracked LLM spend, per-model breakdown, projection, and budget alerts.No findings

    Why it is in this group

    • The description's first verb is "get": a word for reading.
    Description, as the server wrote it
    Get today's tracked LLM spend, per-model breakdown, projection, and budget alerts. Free — no credits charged.

    Annotations the server declares

    • title: Get daily spend and budget
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • rigor_statusCheck the status of a running or completed Rigor workflow.No findings

    Why it is in this group

    • The name "rigor_status" says "status": a word for reading.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Check workflow status
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false
  • rigor_workflowsList and search Rigor workflows for your organization, with filtering and pagination.Reads private dataNo findings

    Why it is in this group

    • The description's first verb is "list": a word for reading.

    What it can reach

    • private-dataThe input names a folder (input.folder_id), and the tool reads: it reads files.
    Description, as the server wrote it
    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 stuck or completed workflows, and — via q — find prior work on a subject before commissioning it again. Pair a q hit with rigor_status to read that workflow's deliverable.

    Annotations the server declares

    • title: List Rigor workflows
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: false

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

7 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 outbound tool breaks every one.

Reads private data1
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write7
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out1
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
deny to break every path
{
  "permissions": {
    "deny": [
      "mcp__plith__rigor_execute"
    ]
  }
}

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 18:27 UTC, unchanged since Nov 13, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
2
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
https://plith.ai/.well-known/oauth-protected-resource
Authorization servers
https://plith.ai
Legacy HTTP+SSE transport
no
Dynamic client registration
yes
Client ID metadata documents
yes
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://plith.ai/api/mcp: tools/list returned 4 tools to an anonymous client, including rigor_plan (write), rigor_execute (write)

    What this check looks for

Posture changes

  1. Nov 13, 2026
    • Tools that change things, listed without credentials: 12 to 2
    • RFC 9728 protected resource metadata: none to https://plith.ai/.well-known/oauth-protected-resource
    • Authorization servers: none to https://plith.ai
    • Dynamic client registration: not observed to yes
    • Client ID metadata documents: not observed to yes
  2. Nov 6, 2026
    • Protocol version: 2024-11-05 to 2025-06-18

Findings

Matches of fixed checks, with the text they matched.

4 warn
  • The server marks "burnrate_track" as not read-only (readOnlyHint: false), and its words say it reads.

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "log": a word for reading.

    What this check looks for
  • The server marks "burnrate_optimize" as not read-only (readOnlyHint: false), and its words say it reads.

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "get": a word for reading.

    What this check looks for
  • The server marks "qualitygate_validate" as not read-only (readOnlyHint: false), and its words say it reads.

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "qualitygate_validate" says "validate": a word for reading.

    What this check looks for
  • The server marks "pitfalldb_query" as not read-only (readOnlyHint: false), and its words say it reads.

    Matched text

    annotations: {"readOnlyHint":false,"destructiveHint":false,"idempotentHint":true,"openWorldHint":true}; The name "pitfalldb_query" says "query": a word for reading.

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

  1. PostureRemote posture changed. Tools that change things, listed without credentials: 12 -> 2; RFC 9728 protected resource metadata: none -> https://plith.ai/.well-known/oauth-protected-resource; Authorization servers: none -> https://plith.ai (and…View diff
    • Tools that change things, listed without credentials: 12 to 2
    • RFC 9728 protected resource metadata: none to https://plith.ai/.well-known/oauth-protected-resource
    • Authorization servers: none to https://plith.ai
    • Dynamic client registration: not observed to yes
    • Client ID metadata documents: not observed to yes
  2. PostureRemote posture changed. Protocol version: 2024-11-05 -> 2025-06-18.View diff
    • Protocol version: 2024-11-05 to 2025-06-18

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

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

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__plith__burnrate_budget",
      "mcp__plith__rigor_status",
      "mcp__plith__rigor_workflows"
    ],
    "ask": [
      "mcp__plith__dedupq_check",
      "mcp__plith__dedupq_complete",
      "mcp__plith__burnrate_estimate",
      "mcp__plith__burnrate_track",
      "mcp__plith__burnrate_optimize",
      "mcp__plith__qualitygate_validate",
      "mcp__plith__guardrail_check",
      "mcp__plith__guardrail_create_policy",
      "mcp__plith__pitfalldb_query",
      "mcp__plith__pitfalldb_report",
      "mcp__plith__rigor_plan",
      "mcp__plith__rigor_execute"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as plith. Review it before you use it.

Capability tags behind 8 rules
  • mcp__plith__dedupq_check untrusted-input
  • mcp__plith__dedupq_complete untrusted-input
  • mcp__plith__qualitygate_validate untrusted-input
  • mcp__plith__pitfalldb_query untrusted-input
  • mcp__plith__pitfalldb_report untrusted-input
  • mcp__plith__rigor_plan untrusted-input
  • mcp__plith__rigor_execute untrusted-input, outbound
  • mcp__plith__rigor_workflows private-data

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/ai.plith/plith/verify?hash=fa693d7a22c464ebd06ef8425361287d5705bd2ecc6938563ebf97d8bacf9ecd" | jq -e '.changed == false'

Pinned hash fa693d7a22c4, from Nov 10, 2026, 04:17 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/ai.plith/plith/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for ai.plith/plith
[![Anlyon Radar](https://radar.anlyon.com/badge/ai.plith/plith.svg)](https://radar.anlyon.com/servers/ai.plith/plith)

Source: MCP Registry · repository. Synced Oct 24, 2026, 23:17 UTC.

plith MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the plith MCP server safe?

No scan can promise that. What its definitions show: 15 tools, 12 of which can change, send or delete something, and 4 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the plith MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the plith MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the plith MCP server have?

15 tools: 12 write, 3 read. dedupq_check, dedupq_complete, burnrate_estimate, burnrate_track, burnrate_optimize, qualitygate_validate, guardrail_check, guardrail_create_policy and 7 more.

Does the plith MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the plith MCP server send data to outside services?

1 tool can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): rigor_execute.

Has the plith MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 10, 2026.