PdfParse
Server Details
Extract PDFs into structured tables, query records, and configure document inbox workflows.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- PabloG6/pdfparse-integrations
- GitHub Stars
- 0
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 29 tools
Most tools are distinct, but several overlap: documents.upload and documents.upload_file both ingest PDFs, analysis.credit_memo and analysis.crosscheck both analyze extracted rows (credit_memo includes crosscheck internally), and workflow.setup duplicates granular create tools for tables, routing rules, and splitters. connection.info and connection.profile also both return account identity. Descriptions help, but agents must choose carefully.
The set uses consistent lower snake_case with dotted group prefixes, and most tools follow a group.action pattern such as documents.get, tables.create, and splitters.publish. Minor deviations exist: connection.info, connection.profile, and analysis.credit_memo are noun-like rather than verb_noun, but the overall convention is predictable.
29 tools is heavy for an MCP server, with duplication across splitter types (10 splitter tools), two upload variants, and a composite workflow.setup alongside granular create tools. The domain is complex and each tool has a role, but consolidation is clearly possible.
The core extraction workflow is covered: upload, routing rules, splitters, jobs, tables, row search, and analysis. However, notable lifecycle gaps remain: no document list or delete, no table update or delete, no standalone inbox create/update/delete, and no job list or cancel. These missing administration operations can create dead ends.
Available Tools
29 toolsanalysis.credit_memoAnalysis Credit MemoARead-onlyIdempotentInspect
Generates a first-pass commercial loan credit memo with citations from already extracted rows, returning the memo in this call. Includes a crosscheck internally. Does not run or wait for extraction or save changes. Requires mcp:read and sends bounded row evidence to an external model: at most 80 rows from the first 200 matches, with long values shortened. Returns evidence coverage metadata and assumptions.
Inputs: table_id (required), memo_profile (required), job_id, filters, +1 more. Returns: evidence, sections, risk_score, assumptions, +1 more
analysis.crosscheckAnalysis CrosscheckARead-onlyIdempotentInspect
Analyzes already extracted rows for consistency issues and underwriting risk contradictions, returning findings with row and field references in this call. Does not run or wait for extraction or save changes. Requires mcp:read and sends bounded row evidence to an external model: at most 80 rows from the first 200 matches, with long values shortened. Returns evidence coverage metadata.
Inputs: table_id (required), job_id, filters, project_slug. Returns: summary, evidence, mismatches
connection.infoConnection InfoARead-onlyIdempotentInspect
Returns the connected PdfParse account ID and its available projects, including project IDs, names, and slugs.
Inputs: no named parameters. Returns: user_id, projects
connection.profileConnection ProfileARead-onlyIdempotentInspect
Returns the stable, opaque ID of the connected PdfParse account.
Inputs: no named parameters. Returns: id
documents.getDocuments GetARead-onlyIdempotentInspect
Returns a saved document by file_id or numeric document_id, including its numeric ID, status, destination table, extraction job IDs, and processing runs. At least one document identifier is required.
Inputs: file_id, document_id, project_slug. Returns: document, next_action
documents.uploadDocuments UploadAInspect
Uploads and saves a PDF from base64 file bytes. With tableSlug, attempts to create an extraction job immediately, returning job on success or job_error on failure. Without tableSlug, automatic processing uses project routing rules or an active splitter. Returns document identifiers and processing details. Maximum decoded file size: 8 MiB.
Inputs: filename (required), data_base64 (required), tableSlug, project_slug. Returns: job, fileId, status, file_id, +5 more
documents.upload_fileDocuments Upload FileAInspect
Uploads and saves a user-selected ChatGPT PDF attachment from an approved HTTPS file host. With tableSlug, attempts to create an extraction job immediately, returning job on success or job_error on failure. Without tableSlug, automatic processing uses project routing rules or an active splitter. Returns document identifiers and processing details. Maximum file size: 8 MiB.
Inputs: file (required), tableSlug, project_slug. Returns: job, fileId, status, file_id, +5 more
inboxes.listInboxes ListARead-onlyIdempotentInspect
Lists existing email inboxes in owned projects, including inbox IDs, addresses, and names.
Inputs: project_slug. Returns: inboxes
jobs.createJobs CreateBInspect
Start extraction for documents already uploaded to a table.
Inputs: tableSlug (required), documentKeys (required), project_slug. Returns: job
jobs.getJobs GetBRead-onlyIdempotentInspect
Returns an extraction job in an owned project.
Inputs: job_id (required), project_slug. Returns: job
projects.createProjects CreateBInspect
Create an empty project in the connected PdfParse account. Returns its ID and slug for subsequent table and workflow setup.
Inputs: name (required). Returns: project
routing_rules.createRouting Rules CreateBInspect
Create a rule that recognizes a document type and routes it to an extraction table. The table must belong to this project.
Inputs: name (required), prompt (required), tableId (required), enabled, +2 more. Returns: routing_rule
routing_rules.deleteRouting Rules DeleteCDestructiveInspect
Delete a routing rule from a project.
Inputs: rule_id (required), project_slug. Returns: result
routing_rules.listRouting Rules ListARead-onlyIdempotentInspect
List document classification rules and their destination tables in a project.
Inputs: project_slug. Returns: routing_rules
routing_rules.updateRouting Rules UpdateCDestructiveInspect
Change a routing rule, including its prompt, destination, confidence threshold, or enabled state.
Inputs: rule_id (required), name, prompt, enabled, +3 more. Returns: routing_rule
rows.searchRows SearchBRead-onlyIdempotentInspect
Returns paginated extracted rows from a table in an owned project, with optional filters and ordering.
Inputs: table_id (required), page, filters, orderBy, +2 more. Returns: rows
splitters.archiveSplitters ArchiveBDestructiveInspect
Archive a splitter to stop using it for future documents.
Inputs: splitter_id (required), project_slug. Returns: result
splitters.create_logicalSplitters Create LogicalAInspect
Creates an inactive logical splitter draft for mixed PDF attachments. sourceInboxId binds it to one inbox; null applies to project uploads. Routing uses project routing rules. The draft becomes active only after publication.
Inputs: name (required), config (required), description, project_slug. Returns: splitter
splitters.create_page_rangeSplitters Create Page RangeCInspect
Create a splitter draft with fixed page ranges and project-owned destination tables.
Inputs: name (required), config (required), description, project_slug. Returns: splitter
splitters.getSplitters GetBRead-onlyIdempotentInspect
Returns a splitter draft and its published versions.
Inputs: splitter_id (required), project_slug. Returns: splitter
splitters.listSplitters ListARead-onlyIdempotentInspect
List page-range and logical splitters, including drafts and published versions, in a project.
Inputs: project_slug. Returns: splitters
splitters.publishSplitters PublishCDestructiveInspect
Publish a splitter draft. A logical splitter becomes active for its source inbox or project uploads.
Inputs: splitter_id (required), expected_draft_revision (required), project_slug. Returns: publication
splitters.run_page_rangeSplitters Run Page RangeCInspect
Run a published fixed page-range splitter on a document in this project.
Inputs: document_id (required), splitter_id (required), version, project_slug. Returns: run
splitters.test_page_rangeSplitters Test Page RangeBRead-onlyIdempotentInspect
Preview page assignments and review flags for a fixed page-range splitter without saving a run.
Inputs: page_count (required), splitter_id (required), version, project_slug. Returns: preview
splitters.update_logicalSplitters Update LogicalCDestructiveInspect
Updates a logical splitter draft. expected_draft_revision must match its current draft revision.
Inputs: name (required), config (required), splitter_id (required), expected_draft_revision (required), +2 more. Returns: splitter
splitters.update_page_rangeSplitters Update Page RangeCDestructiveInspect
Update a fixed page-range splitter draft using its current draft revision.
Inputs: splitter_id (required), expected_draft_revision (required), name, config, +2 more. Returns: splitter
tables.createTables CreateBInspect
Creates a table with extraction columns in an owned project. An integer primary key named id is added automatically and generated by the database during extraction.
Inputs: name (required), columns (required), project_slug. Returns: table
tables.listTables ListARead-onlyIdempotentInspect
Lists tables in an owned project, including their extraction columns. project_slug is required for accounts with multiple visible projects.
Inputs: project_slug. Returns: tables
workflow.setupWorkflow SetupAIdempotentInspect
Provisions one new table and routing rule, plus an optional new inbox and published logical splitter, in an existing owned project. With dry_run: true, validates ownership, table-name collisions, and splitter conflicts without creating resources; blocked previews return blockers. Both preview and apply require mcp:write. Repeating the same intent resumes saved progress.
Inputs: goal (required), table (required), project (required), routing_rule (required), +3 more. Returns: goal, status, blockers, setup_id
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Turn PDFs, scans and photos into a queryable database. Invoices, CVs, receipts, in bulk.
Turn documents into structured data: parse, extract, classify, split, and fill PDF forms.
Turn documents into verified, structured data: fields, tables, and automatic checks.
Extract text, tables and metadata from every PDF linked in a dataset, CSV or Google Sheet.
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables extraction of structured invoice, purchase order, and contract fields from PDFs, including line items and OCR for scanned pages, without AI.1522 npmMIT
- FlicenseNot gradedqualityCmaintenanceEnables accounts payable teams to extract invoice data from PDFs and images, detect duplicates, normalize vendor names, calculate payment terms, and validate invoice completeness. Supports local extraction for text PDFs and optional vision providers for scanned documents.-
- FlicenseNot gradedqualityCmaintenanceEnables reading entire PDF documents into validated structured JSON, including tables, key-values, and markdown, with read-only extraction tools and layout reconstruction.-
- AlicenseAqualityCmaintenanceProvides deterministic, schema-driven structured data extraction from PDF documents via regex/heuristic matching, enabling repeatable, inspectable, and cost-free field extraction without LLM API calls.3MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.