Name: Plith
Author: plith

Plith MCP

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

not scanned Remote · Streamable HTTP No auth needed 15 tools v1.0.0

No reviews yet by plith The publisher’s own endpoint — this marketplace is not in the path

tools declared

—

trust score

remote

at its publisher

—

calls last 7d

What it does

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

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user --transport http plith-mcp https://plith.ai/api/mcp

# 2 — ask your agent for something these tools do
#   dedupq_check, dedupq_complete, burnrate_estimate and 12 more

Plith costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publishernot claimed

plith1 server

1 category

All 1 server

Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.

Tool surface

What the model actually sees. Descriptions are diffed on every release — see version history.

Only tools that write or reach the network

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.

Parameter	Type	Required	Notes
content	string	yes	The task content to check for duplicates. This is hashed and embedded for matching.
task_id	string	no	Optional caller task ID for tracing and cross-referencing with BurnRate.
hash_only	boolean	no	If true, skip vector similarity search and use exact hash matching only. Default: false.
similarity_threshold	number	no	Cosine similarity threshold for semantic matching, 0.0 to 1.0. Default: 0.80.

After executing a task, store the result so future identical or similar tasks return a cache hit via dedupq_check. Costs 2 credits.

Parameter	Type	Required	Notes
content	string	yes	Original task content. Used to compute hash and embedding for future matching.
result		yes	The task result to cache. Can be any JSON value.
task_id	string	no	Optional task ID. Used as the database row ID if provided.
hash_only	boolean	no	If true, skip embedding generation. Default: false.

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.

Parameter	Type	Required	Notes
plan	array	yes	Array of plan steps with provider, model, and token estimates.

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.

Parameter	Type	Required	Notes
provider	string	yes	LLM provider identifier. Supported: anthropic, openai, google, mistral, cohere, deepseek, together, fireworks, groq. Must match the provider of the model used.
model	string	yes	Model identifier as returned by the provider. Examples: claude-sonnet-4-6, gpt-4o, gemini-2.0-flash, mistral-large-latest. Unknown models are accepted but cost may show as $0.
input_tokens	number	yes	Actual prompt tokens used. Must be >= 0.
output_tokens	number	yes	Actual completion tokens used. Must be >= 0.
task_id	string	no	Optional task ID for cross-referencing spend with DedupQ deduplication results. Use the same task_id passed to dedupq_check to link cost tracking with deduplication.
cache_read_tokens	number	no	Optional. Cache-read tokens.

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.

Parameter	Type	Required	Notes
plan	array	yes	Array of plan steps. Same schema as burnrate_estimate: each step needs step, provider, model, estimated_input_tokens, estimated_output_tokens.
target_budget	number	no	Optional. Target total cost in USD.

Get today's tracked LLM spend, per-model breakdown, projection, and budget alerts. Free — no credits charged.

Parameter	Type	Required	Notes
daily_limit	number	no	Optional. Daily budget in USD (e.g., 10.0 for a $10/day cap). Enables budget alerts and remaining-balance calculation.

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

Parameter	Type	Required	Notes
output	string	yes	The agent output text to validate.
directives	array	no	Directive objects. Types: must_include, must_not_include, must_match, must_not_match, must_contain, must_not_contain, min_length, max_length.
schema	object	no	JSON Schema to validate output against.
language	string	no	Code language for syntax check: json, python, javascript, typescript.
check_types	array	no	Checks to run. Auto-inferred if omitted.
override	boolean	no	Force pass. Requires override_reason.
override_reason	string	no	Required when override is true.

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.

Parameter	Type	Required	Notes
agent_id	string	yes	Agent identifier.
proposed_action	object	yes	Action to evaluate. Must contain a 'type' field. Example: {"type": "http_request", "url": "https://external.example.com"} or {"type": "file_write", "path": "/etc/config"}.

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 I

Parameter	Type	Required	Notes
name	string	yes	Unique policy name per org. Examples: 'no-delete-in-prod', 'budget-cap-50', 'pii-block'.
description	string	no	Optional human-readable summary of what this policy enforces. Returned in guardrail_check responses and guardrail_list_policies output for auditability.
rules	array	yes	Array of rule objects evaluated against the proposed_action in guardrail_check. Leaf operators: eq, starts_with, contains, gt, lt (compare field to value). Compound operators: and, or, not (nest sub-r
action_types	array	no	Optional. Restrict this policy to only evaluate when proposed_action.type matches one of these values. Examples: ['file_write', 'api_call', 'db_delete']. Omit to apply the policy to all action types r
priority	number	no	Optional. Evaluation order. Default: 0.

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.

Parameter	Type	Required	Notes
task_type	string	yes	Task category: code_generation, web_search, data_analysis, etc.
task_description	string	no	Optional. Natural-language task description for semantic search.
filters	object	no	Optional filters.

Report an agent failure. PII-scrubbed before storage. Linked to existing pitfalls if similar. Free — no credits charged.

Parameter	Type	Required	Notes
task_type	string	yes	Task category.
task_description	string	yes	Description of the failed task.
failure	object	yes	Failure details.

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.

Parameter	Type	Required	Notes
task_description	string	yes	Natural language description of the task, at most 4,000 characters. Be specific — include what you want produced, constraints, and context. Example: 'Design a caching layer for our API gateway with Re
task_type	string	no	Optional hint to bypass automatic classification. Passing it also removes the slowest classification tiers from the critical path, so send it whenever you know the shape. Multi-step deliverable types:
preferences	object	no	Optional workflow preferences.
prior_workflow_id	string	no	Optional: the workflow_id (wr_…) of a finished workflow in your workspace to build on. Its results are passed to this run as context. It is charged as a new run at the normal quote.
context_fields	array	no	Optional, with prior_workflow_id: the fields to carry over. Pass ["full_step_results"] for every step output in full.

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

Parameter	Type	Required	Notes
task_description	string	yes	Natural language description of the task, at most 4,000 characters. Be specific — include what you want produced, constraints, and context. Example: 'Design a caching layer for our API gateway with Re
task_type	string	no	Optional hint to bypass automatic classification. Passing it also removes the slowest classification tiers from the critical path, so send it whenever you know the shape. Multi-step deliverable types:
delivery	object	no	Delivery method. Default: polling (MCP clients typically can't handle SSE).
preferences	object	no	Optional workflow preferences.
context	object	no	Additional context for the workflow.
prior_workflow_id	string	no	Optional: the workflow_id (wr_…) of a finished workflow in your workspace to build on. Its results are passed to this run as context. It is charged as a new run at the normal quote.
context_fields	array	no	Optional, with prior_workflow_id: the fields to carry over. Pass ["full_step_results"] for every step output in full.

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.

Parameter	Type	Required	Notes
workflow_id	string	yes	The workflow ID returned by rigor_execute (format: wr_xxx).

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 de

Parameter	Type	Required	Notes
status	string	no	Filter by status (comma-separated). Valid values: executing, step_executing, completed, failed, halted, pending_approval, cancelled. E.g. "halted,failed,pending_approval"
task_type	string	no	Filter by classified task type
q	string	no	Search the workflow title and task description. Every whitespace-separated term must appear in one or the other, as a case-insensitive substring — so "vector search postgres" matches a task described
folder_id	string	no	Filter by folder ID. Pass "unassigned" for workflows in no folder
created_after	string	no	ISO timestamp — only workflows created after this time
created_before	string	no	ISO timestamp — only workflows created before this time
counts_toward_limit	string	no	Filter to workflows counting toward the concurrent limit
limit	number	no	Page size (default 20, max 100)
cursor	string	no	Pagination cursor (created_at timestamp from previous page)

Free

$0 forever

Every tool — any call limit is its publisher’s, not ours
No card, and mcprush charges nothing for it
Runs at its publisher’s own address — this marketplace is not in the path
Nothing to cap, because mcprush bills nothing

Nothing here is billable: mcprush charges nothing to install Plith or to call it, at any volume.

Where are you running it?

Tool surface

Release history

Plith MCP

What it does

Quickstart

Where are you running it?

Tool surface

What counts against your monthly calls

Release history

See also