ParseRail MCP
ParseRail MCP exposes ~50 credit-metered tools that turn a single MCP server into document AI, business-ops automation, content generation, and media handling.
Document parsing → structured JSON:
parserail_parse(invoice/EOB/ERA/COI from PDF/image/text), plus specializedparserail_invoice,parserail_receipt,parserail_statement,parserail_resume,parserail_tables, andparserail_split(classify + split multi-doc bundles). Inputs accept rawtext, a publicfileUrl, orfileBase64+fileMimeType.Text intelligence:
parserail_extract(your named fields, typed + confidence),parserail_classify,parserail_categorize(batch, up to ~100 items),parserail_summarize,parserail_sentiment,parserail_redact(PII/PHI),parserail_contract(parties, terms, risk flags),parserail_compare(two doc versions → material changes), andparserail_structure(shape output to your own JSON Schema with validation + retry).Data quality & matching:
parserail_normalize(canonicalize messy records with a change log) andparserail_match(dedupe/entity-resolve two record sets with confidence).Finance & collections ops:
parserail_chargeback(representment packet),parserail_po_match(invoice vs PO vs receipt 3-way match),parserail_dunning(escalating collection sequence),parserail_quote(itemized quote from job + rates),parserail_fraud_flag(risk score and signals).Customer & revenue workflows:
parserail_enrich(domain/email → company profile),parserail_screen(web-grounded ICP qualification),parserail_research(citation-backed briefs),parserail_outreach,parserail_reply,parserail_review_reply,parserail_triage(priority/team/SLA),parserail_minutes,parserail_memory(store/search/forget on your namespace).Content & media:
parserail_moderate(your policy → allow/review/block),parserail_rewrite(brand voice),parserail_product_copy,parserail_describe(alt text/caption/tags/OCR),parserail_transcribe(audio + speakers/timestamps),parserail_image(generation), andparserail_speak(TTS audio).Account & free utilities:
parserail_account(credit balance) andparserail_late_fee_rules(free, statute-cited US state late-fee ceilings). Billing is pay-per-call credits, charged only on success.Caveats: the schema is far larger than the README's 11-tool table, and the documented
parserail_dry_runtool (plus thePARSERAIL_DRY_RUN=1env switch) is absent from the schema, so dry-run cost/balance checking may not be callable as described.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ParseRail MCP Parse this invoice and extract the total due."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
parserail-mcp
An MCP server for ParseRail, gives Claude, Cursor, and any Model Context Protocol client native tools to parse documents, extract fields, redact PII, analyze contracts, fight chargebacks, and enrich companies.
Setup
Get a key at parserail.thecompound.tech. Add the server to your MCP client config. ParseRail has no free tier. Buy credits up front through a $20 pack or a plan from $19/mo. ParseRail charges a call only when it succeeds.
Claude Code:
claude mcp add parserail -e PARSERAIL_API_KEY=ksk_live_… -- npx -y parserail-mcpClaude Desktop / Cursor (mcpServers config):
{
"mcpServers": {
"parserail": {
"command": "npx",
"args": ["-y", "parserail-mcp"],
"env": { "PARSERAIL_API_KEY": "ksk_live_…" }
}
}
}Related MCP server: Enterprise Knowledge MCP Server
Tools
Tool | What it does |
| Document (invoice/EOB/COI, PDF/image/text) → structured JSON |
| Pull named fields out of any text |
| Label text against your taxonomy |
| Summary + key points + action items |
| Strip PII/PHI from text |
| Sentiment, aspects, and themes |
| Contract → parties, terms, obligations, risk flags |
| Dispute details → representment packet |
| Domain or email → company profile |
| Credit balance |
| Check a call's key, body and balance, and see its cost, without running it |
Documents can be passed as fileUrl, raw text, or fileBase64 + fileMimeType.
Dry run
A new key has a zero balance. parserail_dry_run checks a call before you buy credits. It takes an endpoint and a body. It returns wouldCharge, balance and liveStatus, the status a live call would get. It runs no model and costs nothing.
Set PARSERAIL_DRY_RUN=1 in the server's env to make every tool a dry run. Each call then sends ParseRail-Dry-Run: 1.
Pricing
You pay with pay-per-call credits. You do not need a subscription. ParseRail charges you only when a call succeeds. See parserail.thecompound.tech/docs.
MIT, Compound Labs
Available Tools
41 toolsparserail_accountAccount balanceARead-onlyIdempotent
Get the authenticated account's credit balance.
Inputs: no named parameters.
parserail_categorizeBatch categorizationA
Up to a hundred items against your taxonomy in one call, products, transactions, tickets, each with a confidence. Costs credits from the account wallet.
Inputs: items (required), taxonomy (required), multi, instructions.
parserail_chargebackChargeback representmentB
Dispute details → a representment narrative, an evidence checklist, the right reason code, and a win-likelihood. Costs credits from the account wallet.
Inputs: reason (required), transaction (required), context, network, +1 more.
parserail_classifyClassificationB
Route or tag text against your own taxonomy, a label, a confidence, and a one-line rationale. Costs credits from the account wallet.
Inputs: text (required), labels (required), multi, instructions.
parserail_compareDocument comparisonA
Two versions of a contract or document → every material change, what it means, and the risk it carries. Costs credits from the account wallet.
Inputs: a (required), b (required).
parserail_contractContract analysisA
A contract → parties, effective date, term, renewal, governing law, obligations, and flagged risk clauses. Costs credits from the account wallet.
Inputs: text, fileUrl, fileBase64, fileMimeType.
parserail_describeImage descriptionA
An image → accessible alt text, a caption, tags, and any text found inside it. Accessibility and catalogs in one call. Costs credits from the account wallet.
Inputs: image, purpose, imageUrl.
parserail_dunningCollections sequenceA
An overdue invoice → a ready-to-send collection sequence, escalating at the right pace and tone for how late it is. Costs credits from the account wallet.
Inputs: invoice (required), customer (required), tone, steps, +1 more.
parserail_enrichCompany enrichmentA
A domain or work email → a structured company profile: name, description, industry, HQ, size, and links. Costs credits from the account wallet.
Inputs: email, domain.
parserail_extractField extractionA
Pull a field set you define out of any block of text. You name the fields; you get typed values with confidence. Costs credits from the account wallet.
Inputs: text (required), fields (required), instructions.
parserail_fraud_flagFraud triageA
An order or transaction in context → a risk score, the signals driving it, and the checks worth running before you ship. Costs credits from the account wallet.
Inputs: order (required), context.
parserail_imageImage generationA
A prompt → a production-ready image. Marketing visuals, product scenes, and consistent brand imagery. Costs credits from the account wallet.
Inputs: prompt (required), style, aspectRatio.
parserail_invoiceInvoice extractionB
An invoice, PDF, photo, or text, into vendor, dates, PO refs, tax, totals, and clean line items. Costs credits from the account wallet.
Inputs: text, fileUrl, fileBase64, fileMimeType.
parserail_late_fee_rulesUS late-fee ceilings by stateARead-onlyIdempotent
Look up the maximum late-fee/interest rate a US state allows on a commercial (B2B) invoice, with the statute cite. Statute-verified conservative safe floors. Free, costs no credits.
Inputs: state.
parserail_matchEntity matchingA
Two record sets → which rows are the same real-world thing, with confidence and reasoning. Fuzzy names, typos, aliases handled. Costs credits from the account wallet.
Inputs: a (required), b (required), keys.
parserail_memoryAgent memoryA
Store, search, and forget memories for your agents, semantic recall on your own namespace, no vector DB to run. Costs credits from the account wallet.
Inputs: op (required), id, limit, query, +3 more.
parserail_minutesMeeting minutesA
A meeting transcript → clean minutes: summary, decisions made, action items with owners, and open questions. Costs credits from the account wallet.
Inputs: transcript (required), attendees.
parserail_moderateContent moderationA
Text or an image against YOUR policy → allow, review, or block, with the categories and excerpts that drove the call. Costs credits from the account wallet.
Inputs: text, image, policy, imageUrl.
parserail_normalizeRecord normalizationA
A batch of messy records → clean canonical rows, with a change log of every fix (casing, formats, dedup-ready values). Costs credits from the account wallet.
Inputs: records (required), fields, instructions.
parserail_outreachOutreach sequenceB
An enriched lead plus what you sell → a personalized outreach sequence that references what actually makes them a fit. Costs credits from the account wallet.
Inputs: lead (required), product (required), steps, sender, +1 more.
parserail_parseDocument parseA
Any invoice, receipt, EOB, ERA, or COI, PDF or image, into structured, validated JSON. Costs credits from the account wallet.
Inputs: text, docType, fileUrl, fileBase64, +1 more.
parserail_po_match3-way matchA
Invoice vs purchase order vs receipt → matched, partial, or mismatched, with every discrepancy flagged and sized. Costs credits from the account wallet.
Inputs: invoice (required), purchaseOrder (required), receipt, tolerancePct.
parserail_product_copyProduct copyB
Specs and an audience → listing-ready titles, bullets, a description, and SEO keywords, per channel. Costs credits from the account wallet.
Inputs: product (required), channel.
parserail_quoteQuote builderA
A job description plus your rates → an itemized, professional quote with assumptions and scope notes spelled out. Costs credits from the account wallet.
Inputs: job (required), rates, currency, pastQuotes.
parserail_receiptReceipt extractionA
A receipt into merchant, items, totals, payment method, and an expense category, built for expense flows. Costs credits from the account wallet.
Inputs: text, fileUrl, fileBase64, fileMimeType.
parserail_redactPII redactionA
Detect and strip names, emails, phones, SSNs, cards, and PHI from text before you store or log it. Costs credits from the account wallet.
Inputs: text (required), types, placeholder.
parserail_replyReply draftingA
A customer thread plus your context → a ready-to-send reply in the right tone, with an internal note for the agent. Costs credits from the account wallet.
Inputs: thread (required), goal, tone, context, +1 more.
parserail_researchResearch briefA
A company or topic → a multi-source, citation-backed brief: what it is, what changed lately, and what matters. Real web work. Costs credits from the account wallet.
Inputs: query (required), depth, focus.
parserail_resumeResume parsingB
A resume or CV into a structured candidate profile: contact, skills, experience, education, and links. Costs credits from the account wallet.
Inputs: text, fileUrl, fileBase64, fileMimeType.
parserail_review_replyReview responseA
A customer review → a brand-safe public response, the issues to log, and whether it needs human escalation. Costs credits from the account wallet.
Inputs: review (required), rating, business, resolution.
parserail_rewriteBrand-voice rewriteA
Any copy → your brand voice. Describe the voice or paste a sample; get the rewrite and what changed. Costs credits from the account wallet.
Inputs: text (required), goal, voice, length, +1 more.
parserail_screenLead screeningA
A lead plus your ICP criteria → a web-grounded qualification verdict with the evidence for and against. Costs credits from the account wallet.
Inputs: lead (required), criteria (required).
parserail_sentimentSentimentA
Turn a review or support message into a sentiment score, per-aspect breakdown, and the themes driving it. Costs credits from the account wallet.
Inputs: text (required), aspects.
parserail_speakText to speechA
Text → natural speech audio, ready to embed. Voice notes, IVR lines, narration. Costs credits from the account wallet.
Inputs: text (required), pace, voice.
parserail_splitDocument splittingA
A multi-document scan bundle classified and split: what each document is, where it starts and ends, and a summary. Costs credits from the account wallet.
Inputs: text, fileUrl, fileBase64, fileMimeType.
parserail_statementStatement parsingA
A bank or card statement into the account, the period, balances, and every transaction as a normalized row. Costs credits from the account wallet.
Inputs: text, fileUrl, fileBase64, fileMimeType.
parserail_structureStructure to your schemaA
Any messy input, text, HTML, an email, plus YOUR JSON schema → output shaped to it, validated against your required fields and property types, with an automatic corrective retry and a valid flag. Costs credits from the account wallet.
Inputs: input (required), schema (required), instructions.
parserail_summarizeSummarizeA
A meeting transcript, thread, or report → a tight summary, key points, and extracted action items. Costs credits from the account wallet.
Inputs: text (required), length, actionItems.
parserail_tablesTable extractionA
Every table in a document, even scanned, as clean headers and rows, ready for your spreadsheet or DB. Costs credits from the account wallet.
Inputs: text, fileUrl, fileBase64, fileMimeType.
parserail_transcribeTranscriptionA
An audio recording → accurate text with speakers and paragraph timestamps. Meetings, calls, voice notes. Costs credits from the account wallet.
Inputs: audio, diarize, audioUrl, language.
parserail_triageTicket triageA
A support ticket → priority, category, the team it belongs to, sentiment, SLA risk, and a suggested first response. Costs credits from the account wallet.
Inputs: ticket (required), teams, categories.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 41 tools
Most tools have distinct target use cases, but there are several overlapping pairs: summarize/minutes, classify/categorize, parse/invoice/receipt, and reply/outreach/review_reply. Reading the descriptions disambiguates them, but an agent is likely to need to compare closely before selecting.
The parserail_ prefix and snake_case style are consistent, which helps. However, the suffix convention is mixed: bare verbs (parse, split, rewrite), bare nouns (invoice, receipt, memory), and noun-first compounds (po_match, review_reply, product_copy), so there is no predictable verb_noun pattern.
At 41 tools, this is far beyond the typical well-scoped 3-15 tool range. Each endpoint may earn its place in the underlying API, but the MCP surface is too heavy for an agent to navigate easily. It feels like a full API dump rather than a curated set.
For a broad all-purpose AI-processing server, coverage is extensive: documents, audio, images, memory, outreach, finance, and account status are all present. However, because the domain is sprawling and many tools are one-shot generation or dead-end workflows, there is no clear lifecycle for created artifacts. Minor gaps like translation or custom voice selection are noticeable but not severe.
Related MCP Connectors
Hosted document tools for agents: extract, parse, classify, convert, OCR, sign, and redact.
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Pay-per-call document and web tools for AI agents: PDF parsing and OCR (Japanese-strong), web and structured extraction, invoice verification, company profiles and PDF utilities. x402 (USDC on Base), no API key; failed calls are never charged.
Turn documents into structured, AI-ready data by parsing, enriching, chunking, and embedding.
Related MCP Servers
AlicenseAqualityDmaintenanceEnables document parsing into structured, confidence-scored fields via the scan tool, working with any MCP host like Claude Desktop or Cursor.144 npmMIT- AlicenseNot gradedqualityDmaintenanceEnables querying enterprise documents (DOCX, PDF, PPTX) using natural language, with hybrid search and MCP integration for Claude Desktop and other agents.MIT

docuprox-mcpofficial
AlicenseAqualityDmaintenanceEnables AI clients like Claude to process documents (invoices, passports, etc.) via the DocuProx API, with tools for submitting jobs, checking status, and retrieving results.519 npmMIT
flexorch-mcpofficial
AlicenseAqualityBmaintenanceEnables Claude and other MCP-compatible agents to process documents, extract structured data, detect PII, and export LLM-ready datasets through natural language tool calls.821 PyPI1MIT