SpecStream

Name: SpecStream
Author: SpecStream

为您的代理提供结构化的实时网络数据。用简单的语言描述所需的数据，并仅获取符合要求的记录，这些记录是从当前时刻的实时网络中读取的，每个值都附带其来源URL：公司、本地商家、SEC文件、招标、补助金、职位、研究论文等。先报价，然后按结果付费。通过支持OAuth登录或API密钥的可流式传输HTTP远程MCP服务器。

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 · 2026-11-11 20:50）：为您的代理提供结构化的实时网络数据
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。

能力清单

工具	说明
compile	Reads a request for a list, written in everyday words in any language: companies and local businesses, products and stores, jobs, papers, clinical trials, grants, tenders, datasets, repositories and packages, apps, books or podcasts. Returns how SpecStream understood it: what to find, the conditions for every result, the facts to bring back (required or optional), how many, and in what order. The returned ast_hash identifies this reading. For a list the user has, parent_find_id and the operation add facts to it, extend it or refresh it. In that case, what it finds and its conditions stay the same, and only the new facts or the new count are read. The caller needs read access to that list. Nothing runs and nothing is charged.
edit_spec	Changes a condition or a fact to bring back without rewording the request. It takes the revised reading as ast, with the edit operations. Returns a checked reading with a new ast_hash for the next quote. Results that already ran stay as they were.
list_find_rows	Reads the delivered results, one page at a time, with the source behind each condition a page states. A condition no page states yet is listed on its result. next_cursor is null on the last page. Every delivered result is charged. The markdown and csv formats return the asked columns in order as one table, with a source link for each value.
get_find	Reads a run's request, its progress and its cost so far.
get_revisit	Reads one page of the records a recheck looked at: what still holds, what changed, and what it could not reach. next_after is the after value for the next page, and it is null on the last page.
create_spec	Saves a reviewed request as its first version, so it can be rerun, shared or changed.
list_specs	Lists the saved requests the caller can open.
get_spec	Reads a saved request and its current version.
create_spec_link	Creates a link to the wording and conditions of a saved request. The link never shares results or the balance.
get_shared_spec	Reads a request someone shared, while their link is on.
revoke_spec_link	Turns off a shared request link. The request and its results stay.
revise_spec	Saves a change to a saved request as a new version. The save fails if someone changed the request after the caller read it.
list_spec_revisions	Lists every saved version of a request.
get_spec_revision	Reads one earlier version of a saved request, unchanged.
archive_spec	Archives a saved request, or restores it. Its results stay.
list_spec_finds	Lists the runs of each version of a saved request.
get_find_lineage	Reads which version of a request a run used, and the earlier run it continued.
create_project	Creates a project with its own spending limit.
list_projects	Lists the projects the caller can open, with the caller's role in each.
get_project	Reads a project, its members, their roles and their spending limits.
update_project	Changes a project's details. The change fails if someone changed the project after the caller read it.
put_project_member	Sets a person's role in a project, editor or viewer, and their own monthly spending limit.
list_project_members	Lists the people in a project and their roles.
revoke_project_member	Ends a person's access to a project. Their work stays.
get_delivery	Reads a run's finished results with the request version and the sources behind them.
get_find_decisions	Reads each condition check on a run's results: yes, no or unsure, the value seen, and its source.
replay_find_decisions	Reproduces a run's saved checks from the recorded evidence. No new search and no new charge.
get_me	Reads the spending limit for this connection and how much of it is left.
search_workspace	Finds records, lists, requests, projects, people, notes and monitors by name or text.
search_web	Fast search: answers a question from the live web in seconds. Suited to one fact, or to the first rows of a list before the full table is priced. Returns kind (fact or list), the answer with the page it was read from, rows with each result's name and the facts the request asks for, each value with its page, the search results read (sources), took_ms and request_id. For a list, handoff names the estimated rows and the next steps, a compiled request and a quote for the full table. Each call takes $0.005 from the account's balance and needs no quote or approval. A full list is run from a compiled request and its quote, not from this search.
read_pages	Reads up to 20 web pages or documents (PDF, Word, Excel) live and returns each one's main text, as Markdown (format markdown, the default) or plain text (format text), with its title and the date it says it was published. Each result has status: ok, blocked, not_found, empty, unsupported, invalid_url or failed, and read_from: live, or site or archive when the page refused a live read and its site's feed or its newest archive capture gave the text (captured_at says when). A page is charged only when its status is ok, $0.0008 a page from the account's balance, with no quote or approval. It reads the pages a fast search returned or URLs the user gives.
list_web_searches	Lists the account's past fast searches, newest first: each question with when it was asked, its kind (fact or list), the answer and the page it was read from, the number of rows, and the search results its values come from (sources). q keeps the searches whose words contain it. An answer the account already paid for is read here again without a new search. next_cursor leads to older searches. Nothing is charged.
get_web_search	Opens one past fast search by its id, from the account's search history or from the answer of the search itself, exactly as it was given: the answer, the rows with the page of each value, the search results read and, for a list, the hand-off to the full table. Nothing is charged.
list_notifications	Reads mentions, finished work and blocked monitors.
list_audit_events	Reads sign-ins, new keys, approved spending, exports, monitors and imports from the last 12 months.
get_account	Reads the account and its payment history.
spec_options	Lists the conditions and facts SpecStream can check for one kind of record.
get_find_commerce	Reads what a run was charged, what it delivered, and who can open it.
reconcile_find_commerce	Finds a payment that already happened for a run, so the work does not run again.
cancel_find	Asks a run in progress to stop. The run keeps what it already found.
export_find	Creates a download link for a run's results as CSV, Excel, JSON or HTML, or as KML and GeoJSON for records with places. The link works for 24 hours.
share_find	Creates a link to a fixed copy of a run's results. Anyone with the link can open it.
revoke_share	Turns off a shared link to a run's results or to a list.
get_capacity_catalog	Reads the plans, per-result rates and top-up options.
get_capacity_balance	Reads the balance available for work. A balance is not permission to spend. Paid work starts only from a quote the user approved.
get_capacity_entitlements	Reads the account's plan, what it includes, such as schedules, CRM sync and single sign-on, and how many members it has. A feature outside the plan returns plan_required with the plan that includes it.
claim_free_capacity	Claims the one-time free balance for an eligible, verified account.
quote_capacity_work	Prices the reading identified by ast_hash before anything runs. Operation find prices a new request. Operation extend prices more results, add_facts prices more facts on results the user has, and refresh prices a recheck of them. These three take parent_find_id. For an imported list, operation find with source_import_id and its source_row_ids fills in details or checks each row. The quote shows the most the work can cost. Nothing is spent.
get_capacity_quote	Reads a quote and any work already approved from it.
authorize_capacity_work	Starts the work on an approved quote. It takes the quote_id and quote_hash, the ceiling the user approved in cents as confirm_max_cents, and a stable idempotency_key. SpecStream then reads the live web and charges for delivered results at the quoted rate, plus the checks the quote lists, never more than the ceiling.
get_capacity_request	Returns the work started with an idempotency_key, so a retry does not start it twice.
get_capacity_execution	Reads the finished work, what it cost, and the caller's access to its results.
create_capacity_schedule	Runs a request on a schedule, hourly to yearly, within a limit per run and per period. Each run reads the live web. A refresh bills half the rate for a changed row and 1 cent for an unchanged row. monthly_maximum_cents is the most the monitor can spend in one UTC calendar month. It equals the limit per period, and that limit covers both the scheduled runs and the runs started on demand. scheduled_monthly_cents is the most the scheduled runs alone can spend in their busiest UTC calendar month: the number of runs in that month times the limit per run, never more than the limit per period.
list_capacity_schedules	Lists the account's monitors and whether each is running or paused. monthly_maximum_cents is the most a monitor can spend in one UTC calendar month, equal to its limit per period. scheduled_monthly_cents is the most its scheduled runs alone can spend in their busiest UTC calendar month.
update_capacity_schedule	Pauses, resumes or deletes a monitor. Missed runs are never bought later.
list_capacity_occurrences	Reads a monitor's completed, blocked and missed runs, with the reason for each.
create_capacity_refund_claim	Sends charged results that do not meet the request's conditions for review and a refund.
get_capacity_refund_claim	Reads the status of a reported wrong result.
create_api_key	Creates an API key with permissions, an expiry date and a spending limit.
create_webhook	Adds a webhook that sends a signed event to a URL when a run finishes, a monitor finds something new, or records are added. The response shows the signing secret once.
delegate_access	Lets a key or project run specific work within a per-run and monthly limit.
request_account_deletion	Closes the account. Access ends at once, and the data is erased seven days later.
invite_project_member	Emails a project invitation with a role, a spending limit and an expiry date.
filter_by_area	Narrows a collection to the records inside an area on the map.
get_input_research	Reads each original row of an imported list, the identity decision with its source, any unresolved namesakes and the delivered record. The name and location in the input are search hints, not verified facts. An identity without evidence stays missing and is not a Match. No charge and no new research.
set_schedule_delivery	Sets where new and changed records go when a monitor finds them: notifications, Slack, a connected tool or a signed webhook. Nothing runs.
list_collections	Lists the imported lists and results the caller can open.
get_collection	Reads a collection's records, columns and saved views.
combine_collections	Merges collections the caller owns into one, and keeps each record once with its sources.
filter_collection	Keeps the selected records of a collection, by ID, by source or by location.
list_views	Lists the views saved on a collection.
save_view	Saves the filters, columns, sort order and map area of a collection as a personal view.
list_starred	Lists the starred requests, collections and projects.
star_item	Stars or unstars a request, collection or project, so it shows in the sidebar.
list_notes	Reads the notes on a project or a record.
add_note	Adds a note to a project or a record. Each person the note @mentions gets an email.
resolve_note	Marks a note done, or reopens it.
list_your_fields	Reads the status, checkbox and text fields a team added to a collection.
save_your_fields	Adds, renames or removes the team's own fields on a collection. Removing a field deletes its values.
set_your_field	Sets or clears one of the team's own fields on the selected records, such as a status of Called.
list_connections	Lists the spreadsheets, databases, CRMs and automation tools this account connected.
list_connection_destinations	Lists the sheets, tables, bases and CRM objects in a connected account.
get_connection_columns	Reads the columns or properties a destination has, in the tool's own words. Nothing is sent.
save_connection_destination	Saves which fact goes into which field of a destination, for every later send.
send_to_destination	Writes the selected results to Google Sheets, Excel, Airtable, Notion, HubSpot, Salesforce or Outlook drafts with the saved field mapping. A CRM updates the records it already has.
reconcile_destination_export	Checks what arrived in a destination, so nothing is sent twice.
create_destination_sync	Sends new and changed records to one destination on each change, with the same mapping.
update_destination_sync	Starts or stops continuous sending to a destination.
list_destination_syncs	Lists every destination that receives new records, and whether each is on.
list_destination_exports	Reads each send: where it went, how many records arrived, and which were updated or skipped.
list_connected_tools	Lists the sheets, databases, CRMs, automation and chat tools SpecStream can send to.
import_from_source	Imports a Google Sheet, Excel workbook or Airtable view. It can also check the source every day for new and changed rows.
preview_cloud_list	Reads the first rows and columns of a Google Sheet, Excel workbook or Airtable view before an import.
list_cloud_imports	Lists the linked sheets and tables, and when each was last checked.
update_cloud_import	Turns the daily check for new and changed rows on or off for a linked sheet.
import_csv	Imports the user's own list from a CSV or Excel file, with names, websites, places and any other columns. Nothing is researched or charged. Returns the import id, which a quote takes as source_import_id to fill in details or check each row.
list_activity	Reads what happened across the account and its projects, and who did it.
get_relationships	Groups records by the values they share in a column.
save_relationships	Saves the column that links records, such as a city, an owner or a supplier.
report_wrong_result	Reports a wrong charged result in a list, within 7 days, for review and a refund.
share_collection	Creates a link to a fixed copy of every record in a list, such as an imported list. Anyone with the link can open it without an account. Each value keeps the source link its list gives. Nothing is charged. Returns the share id, which turns the link off.
list_request_templates	Lists example requests that work for each kind of record. Nothing runs from an example until a quote for it is approved.
get_collection_changes	Compares a list with its earlier results: each changed fact, before and after, and where it was seen.
teach_web_source	Reads one public page and learns its records from 3 to 8 example rows the user copied from it. Returns a preview and its explanation: how each field is read, which rows are the user's examples and which were inferred, and what happens when the page changes.
list_web_sources	Lists the website sources saved in a project.
get_web_source	Reads a saved website source and how each column is read.
preview_web_source	Reads a saved source's page again and previews its rows. Earlier lists stay unchanged.
get_web_source_preview	Reads one source preview with its rows, cell locations and field explanations.
save_web_source_list	Saves a preview the user reviewed as an imported list, by its preview hash. Saving does not research or spend.
get_reconciliation_fields	Reads the fields of a list the user can open, with example values, for a match against another list. Changes nothing.
list_reconciliations	Lists the latest comparisons that include a list. SpecStream keeps a comparison for 30 days. A list filled from a comparison stays as its own list.
prepare_reconciliation	Proposes which rows in one list correspond to rows in another list. It takes matching groups of exact or close-spelling rules, and conflict fields that rule a pair out. A pair matches when every rule in one group agrees. Returns the proposed pairs, alternatives, conflicts and missing values. A close spelling is not proof of the same company, and a single candidate is not a chosen pair. No search and no charge.
get_reconciliation	Reads the proposed pairs, alternatives, conflicts and missing values of a comparison. Returns an error if either list changed after the comparison was prepared.
apply_reconciliation	Fills empty cells into a new list from the counterpart rows of the pairs the user chose. It takes the exact comparison hash. Original cells and lists stay unchanged, and unmatched rows stay in the new list. Filled cells are inputs, not checked results. Research on them needs a normal quote and approval.
get_reconciled_input	Reads, for a list filled from a comparison, which chosen pair filled each cell.
list_investigation_functions	Lists the saved requests in a project that can run once per row.
create_investigation_function	Makes a saved request run once per row, with some of its values as typed inputs. Nothing runs and nothing is charged.
get_investigation_function	Reads a saved request that runs per row, and its typed inputs.
get_investigation_parameters	Lists the values in a saved request that can become inputs.
get_investigation_inputs	Lists the columns of a list with example values, for the choice of which column feeds each input.
list_collection_investigations	Lists the recent runs started from a list.
prepare_investigation_batch	Binds the selected rows to the inputs and returns one quote: the distinct searches, rows with missing inputs, searches reused from earlier work, and one maximum. Nothing runs yet.
get_investigation_batch	Reads each input row, its search status and the list it led to.
approve_investigation_batch	Approves the quote's exact maximum. The searches then run as ordinary finds, within that maximum.
cancel_investigation_batch	Stops searches that did not start, and cancels running ones where possible. Finished results stay with the user.
get_investigation_results	Reads each input row with the results it led to, and their sources. Input values are never sources for results.
prepare_research_rule	Prepares a rule that researches rows when they first become ready or when their inputs change, with a per-run and a total spending limit. Nothing runs until the rule is approved.
list_research_rules	Lists the automatic research rules on a list.
get_research_rule	Reads a rule's limits, what it spent, which rows are waiting, and its recent runs.
approve_research_rule	Approves the rule's total spending limit. Rows that qualify later then run with no new approval, until the rule reaches the limit or the expiry.
patch_research_rule	Pauses, resumes or deletes a rule. A pause holds queued searches, and running searches finish. A resume never raises the limits.
get_research_rule_results	Reads every run of the rule with its input rows and results.

纠错与举报（发现条目失效、署名有误或涉及侵权？）

提交举报 / 纠错

侵权举报经核验成立后，我们会即时下线该条目并删除已存的内容副本。