extend

Name: extend
Author: extend

Turn documents into structured data: parse (OCR to markdown), extract fields, classify, split multi-document bundles, and fill PDF forms across PDFs, images, Office docs, spreadsheets, and emails.

OCR Markdown

该来源不提供完整文件导出（国内平台多为平台内托管），仅存元数据与原链

模型生成摘要（rules/v1 · 2026-09-27 16:50）：Turn documents into structured data: parse (OCR to markdown), extract fields, classify, split multi-document bundles, an…
这是模型对公开材料的总结，不是官方声明，请以原链内容为准。

接入信息

传输形态: http
鉴权方式: 鉴权未知
端点: https://extend--extend.run.tools

鉴权方式未标注，请核对官方文档后再接入——不要直接使用以下片段

{
  "mcpServers": {
    "extend": {
      "url": "https://extend--extend.run.tools"
    }
  }
}

能力清单

工具	说明
extract_data	Extract specific structured values (totals, line items, dates, names, tables) from a document (extract group) using a saved extractor, an inline JSON Schema, or schema-less inference. If the user says "OCR" but wants specific values out, use this tool; for the raw text/markdown of the pages use parse_document instead. Provide exactly one of extractor or config, or omit both for schema-less inference (guided by config.extractionRules when config has no schema; not usable with package). If a saved extractor turns out not to exist, rerun THIS tool without the extractor (schema-less) — do not fall back to parse_document for value extraction. For one merged result across 2-50 related documents, pass package instead of file. detail: "full" returns per-field source citations and confidence — the only way to prove where a value came from (provenance); parsing cannot cite. Creates an extract run: may return status: "running" with a runId — normal, not an error; poll it with get_extract_run. Follow any llmContext guidance included in results.
create_extractor	Create a saved, reusable extractor (extract group). Three starting points, mutually exclusive: config (inline schema — call get_documentation with https://docs.extend.ai/extraction/schema.md BEFORE writing one by hand), cloneExtractorId (copy another extractor's draft config), or generate (Extend writes the schema from 1-5 sample documents plus optional instructions; no docs needed); name alone creates an empty draft. The draft is the only mutable surface — edit it with update_extractor, freeze it with publish_extractor_version, run it with extract_data. Follow any llmContext guidance included in results.
update_extractor	Update an extractor's mutable draft (extract group): rename it and/or replace the draft config (hand-editing the schema? call get_documentation with https://docs.extend.ai/extraction/schema.md first). Published versions are immutable and unaffected — runs pinned to them keep working. Follow any llmContext guidance included in results.
get_extractor	Get an extractor with its draft config, or one specific version's config via version (extract group). Use list_extractors to discover IDs. Follow any llmContext guidance included in results.
list_extractors	List the workspace's extractors, newest first (extract group). Fetch a specific one's config with get_extractor. Follow any llmContext guidance included in results.
list_extractor_versions	List an extractor's published (immutable) versions (extract group). Fetch one version's config with get_extractor. Follow any llmContext guidance included in results.
publish_extractor_version	Publish the extractor's current draft config as a new immutable semver version ("1.2"-style) that runs and evaluations can pin (extract group). releaseType picks the major or minor bump; pass config to publish that config instead of the draft. Published versions never change — keep iterating on the draft. Follow any llmContext guidance included in results.
get_extract_run	Get the state and output of an extract run (extract group) — resume a status: "running" run or inspect a failed one. wait: true blocks until terminal or wait-budget expiry (call again to keep waiting). Follow any llmContext guidance included in results.
list_extract_runs	List recent extract runs, newest first (extract group). Filter rather than paginate: status, extractorId, batchId, fileNameContains. Follow any llmContext guidance included in results.
cancel_extract_run	Cancel a queued or in-flight extract run (extract group). Best-effort: a run already finishing may still complete. Follow any llmContext guidance included in results.
delete_extract_run	Permanently delete an extract run and its stored outputs (extract group). Cannot be undone. Follow any llmContext guidance included in results.
run_extract_batch	Submit up to 1,000 documents as one batch of extract runs (extract group) against a saved processor. Returns a batchId immediately; runs execute async — poll aggregate status with get_extract_batch, and fetch individual results with the extract-run list tool filtered by batchId. Follow any llmContext guidance included in results.
get_extract_batch	Get the aggregate status of an extract batch (extract group) submitted by run_extract_batch. wait: true polls until terminal. Statuses: PENDING, PROCESSING, PROCESSED, FAILED, CANCELLED. Follow any llmContext guidance included in results.
classify_document	Categorize a document into one of a set of types, e.g. MSA vs SOW vs NDA (classify group), using a saved classifier or an inline list of classifications. Provide exactly one of classifier or config. Inline config.classifications must include one entry with type: "other" as the fallback and unique ids per entry. Returns the winning type with a confidence score. Creates a classify run: may return status: "running" with a runId — normal, not an error; poll it with get_classify_run. Follow any llmContext guidance included in results.
create_classifier	Create a saved, reusable classifier (classify group). Start from config (inline classifications list — call get_documentation with https://docs.extend.ai/classification/configuration.md before hand-authoring one) or cloneClassifierId (copy another classifier's draft config) — mutually exclusive; name alone creates an empty draft. There is no generate mode (extractors only). The draft is the only mutable surface — edit it with update_classifier, freeze it with publish_classifier_version, run it with classify_document. Follow any llmContext guidance included in results.
update_classifier	Update a classifier's mutable draft (classify group): rename it and/or replace the draft config (hand-editing it? call get_documentation with https://docs.extend.ai/classification/configuration.md first). Published versions are immutable and unaffected — runs pinned to them keep working. Follow any llmContext guidance included in results.
get_classifier	Get a classifier with its draft config, or one specific version's config via version (classify group). Use list_classifiers to discover IDs. Follow any llmContext guidance included in results.
list_classifiers	List the workspace's classifiers, newest first (classify group). Fetch a specific one's config with get_classifier. Follow any llmContext guidance included in results.
list_classifier_versions	List a classifier's published (immutable) versions (classify group). Fetch one version's config with get_classifier. Follow any llmContext guidance included in results.
publish_classifier_version	Publish the classifier's current draft config as a new immutable semver version ("1.2"-style) that runs and evaluations can pin (classify group). releaseType picks the major or minor bump; pass config to publish that config instead of the draft. Published versions never change — keep iterating on the draft. Follow any llmContext guidance included in results.
get_classify_run	Get the state and output of a classify run (classify group) — resume a status: "running" run or inspect a failed one. wait: true blocks until terminal or wait-budget expiry (call again to keep waiting). Follow any llmContext guidance included in results.
list_classify_runs	List recent classify runs, newest first (classify group). Filter rather than paginate: status, classifierId, batchId, fileNameContains. Follow any llmContext guidance included in results.
cancel_classify_run	Cancel a queued or in-flight classify run (classify group). Best-effort: a run already finishing may still complete. Follow any llmContext guidance included in results.
delete_classify_run	Permanently delete a classify run and its stored outputs (classify group). Cannot be undone. Follow any llmContext guidance included in results.
run_classify_batch	Submit up to 1,000 documents as one batch of classify runs (classify group) against a saved processor. Returns a batchId immediately; runs execute async — poll aggregate status with get_classify_batch, and fetch individual results with the classify-run list tool filtered by batchId. Follow any llmContext guidance included in results.
get_classify_batch	Get the aggregate status of a classify batch (classify group) submitted by run_classify_batch. wait: true polls until terminal. Statuses: PENDING, PROCESSING, PROCESSED, FAILED, CANCELLED. Follow any llmContext guidance included in results.
split_document	Divide a combined file, e.g. a scanned bundle of invoices or a merged PDF of statements, into typed segments with page ranges (split group), using a saved splitter or inline split classifications. Also the right FIRST step to locate one document or section inside a larger bundle — split, then parse/extract only the relevant segment instead of processing the whole file. Provide exactly one of splitter or config; inline config.splitClassifications needs a type: "other" entry. Each split includes startPage/endPage and, when Extend materializes child files, a fileId usable directly in other tools. Raw text input is not supported — splitting is page-based. Creates a split run: may return status: "running" with a runId — normal, not an error; poll it with get_split_run. Follow any llmContext guidance included in results.
create_splitter	Create a saved, reusable splitter (split group). Start from config (inline split classifications — call get_documentation with https://docs.extend.ai/splitting/configuration.md before hand-authoring one) or cloneSplitterId (copy another splitter's draft config) — mutually exclusive; name alone creates an empty draft. The draft is the only mutable surface — edit it with update_splitter, freeze it with publish_splitter_version, run it with split_document. Follow any llmContext guidance included in results.
update_splitter	Update a splitter's mutable draft (split group): rename it and/or replace the draft config (hand-editing it? call get_documentation with https://docs.extend.ai/splitting/configuration.md first). Published versions are immutable and unaffected — runs pinned to them keep working. Follow any llmContext guidance included in results.
get_splitter	Get a splitter with its draft config, or one specific version's config via version (split group). Use list_splitters to discover IDs. Follow any llmContext guidance included in results.
list_splitters	List the workspace's splitters, newest first (split group). Fetch a specific one's config with get_splitter. Follow any llmContext guidance included in results.
list_splitter_versions	List a splitter's published (immutable) versions (split group). Fetch one version's config with get_splitter. Follow any llmContext guidance included in results.
publish_splitter_version	Publish the splitter's current draft config as a new immutable semver version ("1.2"-style) that runs and evaluations can pin (split group). releaseType picks the major or minor bump; pass config to publish that config instead of the draft. Published versions never change — keep iterating on the draft. Follow any llmContext guidance included in results.
get_split_run	Get the state and output of a split run (split group) — resume a status: "running" run or inspect a failed one. wait: true blocks until terminal or wait-budget expiry (call again to keep waiting). Follow any llmContext guidance included in results.
list_split_runs	List recent split runs, newest first (split group). Filter rather than paginate: status, splitterId, batchId, fileNameContains. Follow any llmContext guidance included in results.
cancel_split_run	Cancel a queued or in-flight split run (split group). Best-effort: a run already finishing may still complete. Follow any llmContext guidance included in results.
delete_split_run	Permanently delete a split run and its stored outputs (split group). Cannot be undone. Follow any llmContext guidance included in results.
run_split_batch	Submit up to 1,000 documents as one batch of split runs (split group) against a saved processor. Returns a batchId immediately; runs execute async — poll aggregate status with get_split_batch, and fetch individual results with the split-run list tool filtered by batchId. Follow any llmContext guidance included in results.
get_split_batch	Get the aggregate status of a split batch (split group) submitted by run_split_batch. wait: true polls until terminal. Statuses: PENDING, PROCESSING, PROCESSED, FAILED, CANCELLED. Follow any llmContext guidance included in results.
parse_document	Convert a document (PDF, image, Office doc, spreadsheet) into clean structured text — markdown by default (parse group). Right when the user wants the content of the pages ("OCR this", "what does this document say", feed text to another step); for specific field values — or when values need source citations/provenance — use extract_data instead. No saved resource needed. NEVER pull a whole multi-page document into context when only a section matters: pass pageRange to return just those pages, or split_document the bundle first and parse only the relevant segment's fileId — this applies even when you have not yet located the section. Full output of a long document is large — maxChars caps it; rawBlocks returns block-level structure (tables, figures, coordinates). Creates a parse run: may return status: "running" with a runId — normal, not an error; poll it with get_parse_run. Parse runs cannot be cancelled. Follow any llmContext guidance included in results.
get_parse_run	Get the state and output of a parse run (parse group) — resume a status: "running" run or inspect a failed one. wait: true blocks until terminal or wait-budget expiry (call again to keep waiting). Supports pageRange/maxChars/rawBlocks output slicing as in parse_document. Follow any llmContext guidance included in results.
list_parse_runs	List recent parse runs, newest first (parse group). Filter rather than paginate: status, batchId, fileNameContains. Results come back in the upstream default order — this endpoint does not support sorting. Follow any llmContext guidance included in results.
delete_parse_run	Permanently delete a parse run and its stored outputs (parse group). Cannot be undone. Follow any llmContext guidance included in results.
run_parse_batch	Submit up to 1,000 documents as one batch of parse runs (parse group); no saved processor needed — an optional inline config applies to every run. Returns a batchId immediately; poll aggregate status with get_parse_batch and fetch individual results with list_parse_runs filtered by batchId. Follow any llmContext guidance included in results.
get_parse_batch	Get the aggregate status of a parse batch (parse group) submitted by run_parse_batch. wait: true polls until terminal. Statuses: PENDING, PROCESSING, PROCESSED, FAILED, CANCELLED. Follow any llmContext guidance included in results.
run_workflow	Start a run of a deployed multi-step workflow on a document (workflows group; not runnable until a version is deployed, or pass version "draft"). Workflow runs commonly take minutes to hours: a status: "running" response is normal, not an error — NEEDS_REVIEW means paused for human review in the dashboard (see dashboardUrl). For one merged run over 2-50 related files, pass package instead of file. outputs injects pre-computed results for specific extractors/classifiers/splitters so the workflow skips recomputing them (not allowed with package). Follow any llmContext guidance included in results.
create_workflow	Create a workflow — a multi-step document pipeline (workflows group): parse → extract/classify/split → validations → human review. name alone creates an empty draft; steps builds the graph up front (call get_documentation with https://docs.extend.ai/workflows/configuring-workflows.md before hand-authoring a step graph). The draft is the only mutable surface — edit with update_workflow, freeze with deploy_workflow_version, run with run_workflow. Follow any llmContext guidance included in results.
update_workflow	Update a workflow's mutable draft (workflows group): rename it and/or replace the entire draft step graph (hand-editing steps? call get_documentation with https://docs.extend.ai/workflows/configuring-workflows.md first). Deployed versions are immutable and unaffected — runs pinned to them keep working. Follow any llmContext guidance included in results.
get_workflow	Get a workflow with its draft step graph, or one specific deployed version's steps via version (workflows group). Use list_workflows to discover IDs. Follow any llmContext guidance included in results.
list_workflows	List the workspace's workflows, newest first (workflows group). Fetch a specific one's step graph with get_workflow. Follow any llmContext guidance included in results.
list_workflow_versions	List a workflow's deployed (immutable) versions — integer deploy numbers with optional names (workflows group). Fetch one version's steps with get_workflow. Follow any llmContext guidance included in results.
deploy_workflow_version	Deploy the workflow's current draft as a new immutable version (workflows group). Unlike extractor/classifier/splitter publishing there is NO releaseType — workflow versions are integer deploy numbers ("1", "2", ...) with an optional display name referenced at run time. Pass steps to deploy that graph instead of the draft. Deployed versions never change — keep iterating on the draft. Follow any llmContext guidance included in results.
get_workflow_run	Get the state and output of a workflow run (workflows group) — resume a status: "running" run or inspect a failed one. wait: true blocks until terminal or wait-budget expiry (call again to keep waiting). Workflow runs commonly take minutes to hours — repeated running responses are normal. Follow any llmContext guidance included in results.
list_workflow_runs	List recent workflow runs, newest first (workflows group). Filter rather than paginate: status, workflowId, batchId, fileNameContains. Workflow batches have no batch-get endpoint — track them here via batchId. NEEDS_REVIEW runs are paused for human review. Follow any llmContext guidance included in results.
cancel_workflow_run	Cancel a queued or in-flight workflow run (workflows group). Best-effort: a run already finishing may still complete. Follow any llmContext guidance included in results.
delete_workflow_run	Permanently delete a workflow run and its stored outputs (workflows group). Cannot be undone. Follow any llmContext guidance included in results.
run_workflow_batch	Submit up to 1,000 documents as one batch of workflow runs (workflows group). Returns a batchId immediately; workflow batches have NO batch-get endpoint — track progress with list_workflow_runs filtered by batchId. Follow any llmContext guidance included in results.
edit_pdf	Fill form fields in a PDF and return the edited file (edit group). Values come from instructions (free-form prose, e.g. "name is Acme Corp; date is 2026-04-15") and/or schema (an edit schema from detect_form_fields with extend_edit:value set per field; extend_edit:image with an image_url for signature images). The document passed here must be the TARGET form, not the source you read values from — parse or extract the source first, then fill. Before authoring a schema fill by hand, call get_documentation with https://docs.extend.ai/editing/configuration.md and follow it. Output is a pointer { id, presignedUrl } to the filled PDF; the URL expires in ~15 minutes (re-fetch with get_file). Inspect runs with get_edit_run. Follow any llmContext guidance included in results.
detect_form_fields	Detect the fillable fields in a PDF form and return an edit schema (edit group): each property is a detected field with its type (text/checkbox/radio/dropdown/signature/table), page index, and bounding box. Use it to see what a form asks for, or as the scaffold for a structured fill — set extend_edit:value on each field and pass the populated schema to edit_pdf. Pass inputSchema to re-run detection against an existing schema (mapping mode) — for the edit-schema rules, call get_documentation with https://docs.extend.ai/editing/configuration.md first. Inspect runs with get_form_detection_run. Follow any llmContext guidance included in results.
get_edit_run	Get the state and output of an edit run (edit group) — resume a status: "running" run or inspect a failed one. wait: true blocks until terminal or wait-budget expiry (call again to keep waiting). Edit runs have no list endpoint — keep the run ID. Follow any llmContext guidance included in results.
get_form_detection_run	Get the state and output of a form detection run (edit group) — resume a status: "running" run or inspect a failed one. wait: true blocks until terminal or wait-budget expiry (call again to keep waiting). Form detection runs have no list endpoint — keep the run ID. Follow any llmContext guidance included in results.
delete_edit_run	Permanently delete an edit run and its stored outputs (edit group). Cannot be undone. Follow any llmContext guidance included in results.
request_file_upload	Create an upload link for the user to add files from their computer (files group). Returns a dashboard URL; the user uploads in their browser and the files land in the target workspace. Call this last in your turn: write the returned link in your reply, then END THE TURN — do not call get_file_upload or any other tool until the user says they are done uploading. Follow any llmContext guidance included in results.
get_file_upload	Check an upload link created by request_file_upload and get the uploaded file ids (files group). Call it on the user's message after they were shown the link — never in the same turn that shared it. Default is one instant status check; wait: true blocks until the user finishes or the wait budget runs out (call again to keep waiting). Follow any llmContext guidance included in results.
get_file	Get a file's metadata and a fresh presigned download URL — expires in ~15 minutes, re-call to refresh (files group). Set contents to also return parsed text; contents: null means "not parsed yet", not an error (run parse_document first). Split-produced child files carry parentSplit (source file, page range) in metadata. Follow any llmContext guidance included in results.
list_files	List files in the workspace, newest first (files group). Filter with nameContains rather than paginating broadly. Use get_file for a download URL or parsed contents. Follow any llmContext guidance included in results.
delete_file	Permanently delete an uploaded file from Extend (files group). Runs that already processed the file keep their outputs, but the file's bytes and parsed contents are gone. This cannot be undone. Follow any llmContext guidance included in results.
create_webhook_endpoint	Register an HTTPS URL to receive Extend events (webhooks group). CRITICAL: the response's signingSecret is shown ONLY on this call — store it immediately; it cannot be retrieved later. Receivers verify HMAC-SHA256 of "v0:{timestamp}:{body}" against it (reject timestamps older than 5 minutes). enabledEvents here are workspace-global and NOT every event type is valid globally: resource-run events such as workflow_run.completed are rejected here and must instead be scoped to a specific resource via create_webhook_subscription (create the endpoint with enabledEvents [], then subscribe it to the workflow/extractor/etc.). Setting up webhooks by hand? Call get_documentation with https://docs.extend.ai/webhooks/configuration.md first. Follow any llmContext guidance included in results.
list_webhook_endpoints	List the workspace's webhook endpoints with their global event lists (webhooks group). Signing secrets are never returned here — they are shown once at creation only. Follow any llmContext guidance included in results.
update_webhook_endpoint	Update a webhook endpoint's URL, name, status (enable/disable deliveries), global event list, or advanced options (webhooks group). The signing secret never changes and is not returned. Follow any llmContext guidance included in results.
delete_webhook_endpoint	Permanently delete a webhook endpoint (webhooks group). This ALSO deletes every subscription attached to it, and deliveries stop immediately. This cannot be undone. Follow any llmContext guidance included in results.
create_webhook_subscription	Subscribe an existing webhook endpoint to events from ONE specific extractor, classifier, splitter, or workflow (webhooks group) — deliveries for other resources are unaffected. Use this instead of global enabledEvents when only some resources matter. Configuration rules: call get_documentation with https://docs.extend.ai/webhooks/configuration.md first (event catalog: https://docs.extend.ai/webhooks/events.md). Follow any llmContext guidance included in results.
list_webhook_subscriptions	List resource-scoped webhook subscriptions, filterable by endpoint or by the watched resource (webhooks group). Follow any llmContext guidance included in results.
update_webhook_subscription	Replace a webhook subscription's event list (webhooks group). The endpoint and watched resource cannot change — delete and recreate the subscription for that. Follow any llmContext guidance included in results.
delete_webhook_subscription	Permanently delete a webhook subscription (webhooks group). The endpoint and its global events are unaffected. This cannot be undone. Follow any llmContext guidance included in results.
create_evaluation_set	Create an evaluation set — a named collection of ground-truth examples scoped to ONE extractor, classifier, or splitter via entityId (evaluations group). The iteration loop: create a set → add items with add_evaluation_items → publish a new version of the resource → run_evaluation against that version → read accuracy metrics with get_evaluation_run. New to evaluations? Call get_documentation with https://docs.extend.ai/evaluation/overview.md first (set authoring in detail: https://docs.extend.ai/evaluation/creating-evaluation-sets.md). Follow any llmContext guidance included in results.
list_evaluation_sets	List evaluation sets, optionally scoped to one extractor/classifier/splitter via entityId (evaluations group). There is no get-by-id tool — this list returns full set objects. Follow any llmContext guidance included in results.
add_evaluation_items	Bulk-add ground-truth examples (1-100 per call) to an evaluation set (evaluations group). Each item pairs an already-uploaded file with the output the resource SHOULD produce for it. Follow any llmContext guidance included in results.
list_evaluation_items	List an evaluation set's items — file pairings only; expected outputs are not included in summaries (evaluations group). Item IDs feed update_evaluation_item / delete_evaluation_item and subset runs. Follow any llmContext guidance included in results.
update_evaluation_item	Replace one evaluation item's expected output (evaluations group). The file pairing cannot change — delete and re-add for that. Follow any llmContext guidance included in results.
delete_evaluation_item	Permanently remove one ground-truth item from an evaluation set (evaluations group). Past run metrics are unaffected. This cannot be undone. Follow any llmContext guidance included in results.
run_evaluation	Run an evaluation set against a version of its resource and score the results against the ground truth (evaluations group). Async: returns immediately with a bpr_... run ID — poll it with get_evaluation_run (NOT a get-batch tool, even though the ID looks like a batch). Defaults to the set's resource at its latest published version; pass entity to pin { id, version: "1.2" \| "latest" \| "draft" }. Follow any llmContext guidance included in results.
get_evaluation_run	Get an evaluation run's status and accuracy metrics — this is the ONLY tool that returns them, not a get-batch tool (evaluations group). An evaluation is an async job: a fresh run reports PROCESSING, so pass wait: true to block until it finishes instead of polling in a loop. Metrics by resource type: extractors { accuracy, fieldMetrics per field path — each field has countExpected/countAccurate, and accuracy is aggregated across items, not per-item }; classifiers { accuracy, classificationMetrics with precision/recall/f1 per type }; splitters { precision, recall, f1, split counts }. Terminal statuses: PROCESSED, FAILED, CANCELLED. Follow any llmContext guidance included in results.
get_me	Return the connected organization, the credential in use, and the granted workspace + environment ("TEST" or "PRODUCTION") targets — exactly the values the required workspaceId/environment arguments on targeted tools accept. Always available; call this first, and again whenever a tool returns UNAUTHORIZED or NOT_FOUND unexpectedly, or after this connection's access changes — resources live per-workspace.
get_documentation	Fetch an Extend docs page as markdown, live from docs.extend.ai. Pass a URL from a tool description, an error's docUrl, or a search_documentation result. Always available, no workspace targeting.
search_documentation	Search the Extend documentation. Returns matching pages with URLs — fetch the most relevant with get_documentation. Always available, no workspace targeting.

extend

接入信息

能力清单

相关资产

Markdown Converter

产品需求质量检查

园区资讯专家

Baoyu Format Markdown

Generate Mindmap

Novel Outliner - 大纲解析器