Skip to main content
Glama

Server Details

Public tenders and contract awards in the UK, US, Canada and EU, and help preparing bids.

If you are the author of this connector, you can claim ownership. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
Status
Healthy
Uptime
100.0% over the last 24 hours
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

B3.4/5.0

Scored across 44 tools

Disambiguation3/5

Most tools target distinct resources or actions, and many descriptions include explicit cross-references such as 'do not use X, use Y'. However, several clusters remain easy to confuse: setup/profile/settings tools (set_up_tenda, finish_setup, save_company_profile, get_tenda_settings, update_tenda_settings), bid drafting tools (start/continue/get/draft/review/rewrite), and automation/watch/alert tools. With 44 tools, an agent must disambiguate many adjacent workflow concepts.

Naming Consistency4/5

Nearly all tools use snake_case and a predictable verb_noun pattern, such as search_tenders, get_tender_details, record_bid_call, and turn_on_automation. There are minor deviations like open_tenda, tenda_changes, open_bid_panel, and the set_up_tenda/finish_setup pair, but the convention remains readable and mostly consistent.

Tool Count2/5

At 44 tools, this is well beyond the typically well-scoped 3–15 range and into the 'too many' band. The domain is rich, but the surface includes internal UI helpers, multiple setup flows, and many adjacent bid/automation/watch operations that make the server heavy for an agent to navigate.

Completeness4/5

The surface covers tender search, details, awards, coverage, pipeline lifecycle, bid calls, sprint steps, drafting/review/rewrite, readiness/fit checks, documents, watches, alerts, automations, settings, and company profile setup. Some lifecycle gaps remain, such as no update/delete company profile, no edit automation rules, and no update watch operation, but most are workaroundable.

Available Tools

44 tools
add_automationAdd an automationAInspect

Use this when the user wants Winquill to do something on its own, again and again: add strong fits to the pipeline, remind people of sprint steps, check a bid before it closes, say what a buyer changed, or send a morning shortlist or a report. Makes one from the library, saved off. Read its rules back to the user; it runs only once turned on with turn_on_automation. Automations never submit a bid, write to a buyer or email anyone outside the team. Needs a Winquill account. Example: {"template":"morning_shortlist"}

Inputs: template (required), asked, changes, workspace. Returns: link, history, library, summary, +4 more

add_tender_documentsRead tender documentsA
Destructive
Inspect

Use this when the user shares text from a tender's documents, or wants Winquill to read the files the buyer published with the notice (read_published, signed in). Returns a checklist of everything the bid must include, each with its file, page and the buyer's own words, and the requirements the notice leaves out, such as turnover, insurance and certifications. When the workspace can use Winquill's AI, it also returns the questions the buyer scores and how they're marked. Not for documents unrelated to a tender. Example: {"tender_reference":"012345-2026","read_published":true}

Inputs: tender_reference (required), text, title, workspace, +1 more. Returns: note, files, found, notRead, +8 more

add_to_pipelineAdd to pipelineA
Idempotent
Inspect

Use this when the user wants to save a tender to their team's pipeline to consider bidding, e.g. "add this to our pipeline" or "let's track the Falkirk cleaning framework". Adds it in Watching, ready for the bid or no-bid call, and says which e-tendering portal the tender is run on. Until the team has said whether it has an account on that portal, the answer asks; pass the question on, and record the reply with record_portal_account. Needs a Winquill account and workspace. Do not use for alerts about new tenders (use watch_tenders) or to record a decision to bid (use record_bid_call).

Inputs: tender_reference (required), workspace, more_references. Returns: added, stage, tender, summary, +2 more

add_winning_bidShare a winning bid with WinquillAInspect

Use this when the user shares a bid their company won, for Winquill to learn from, e.g. after Winquill offers to learn from winning bids. Winquill keeps it in the workspace's Library and learns what worked in it (structure, tone, the evidence it uses) for the bids it drafts. Pass the bid's text as the user shared it, not a link. Needs a Winquill account and workspace. Do not use for the buyer's questions for a new bid (use start_bid_draft or continue_bid_draft).

Inputs: text (required), title, workspace. Returns: link, saved, title, words, +1 more

assess_tender_fitAssess bid fitA
Read-only
Inspect

Use this when the user asks whether their business should bid for a public contract, or which open tenders suit them best. Compares the tender's conditions of participation (turnover, insurance levels, experience and certifications), location and lot sizes with the company's profile, and returns a fit score with reasons, likely disqualifiers and gaps. Omit tender_reference to rank the open tenders that suit the company. It does not predict or guarantee an award. Do not use for general business strategy or for private-sector sales leads.

Inputs: query, country, business_size, company_summary, +2 more. Returns: fit, found, caveat, credit, +5 more

assign_taskGive out bid workA
DestructiveIdempotent
Inspect

Use this when the user gives work on a team bid to someone, or takes it on: "give the Bristol bid call to Sam". The work is the bid call while a tender waits in Watching or Qualifying, or a sprint step, the next one unless named. Says who has it and whether they heard in Slack. When the person's role can't do it, the answer says who can: ask the user before choosing one. Needs a Winquill account and workspace. Not for ticking off a step (use update_bid_sprint) or the call itself (use record_bid_call). Example: {"tender_reference":"012345-2026","person":"Sam","task":"review"}

Inputs: person (required), tender_reference (required), task, workspace. Returns: stage, tender, summary, assigned, +1 more

check_bid_readinessCheck bid documentsA
Read-only
Inspect

Use this when the user wants to know what they're missing before bidding, for one tender or in general: registrations, certifications, insurance, policies and each country's own documents, such as Cyber Essentials in the UK, SAM.gov registration in the US or the DUME in France. A general check follows the user's home country. Returns what is held, missing or expiring. It gives readiness guidance, not legal advice. Not for Companies House look-ups or tax questions. Example: {"tender_reference":"003344-2026","documents_held":["cyber_essentials","iso_9001"]}

Inputs: sector, country, documents_held, tender_reference. Returns: found, caveat, credit, tender, +4 more

choose_alertsChoose where Winquill's alerts goA
DestructiveIdempotent
Inspect

Use this when the user wants to change which Slack and Teams channels get Winquill's alerts, or asks where they go: "stop the morning summary in Slack". Change only what the user asked for; with neither send nor stop it changes nothing and says where alerts go now. Owners and admins can change alerts. Needs a Winquill account and workspace. Not for connecting a channel (Winquill dashboard, Settings, Connections) or for email alerts (use watch_tenders). Example: {"app":"slack","stop":["morning_summary"]}

Inputs: app, only, send, stop, +2 more. Returns: link, summary, channels

continue_bid_draftCarry on Winquill's bid draftA
Destructive
Inspect

Use this to carry on a bid draft Winquill started with start_bid_draft: give it the buyer's questions it asked for, the team's answers to the questions Winquill asked, or the go-ahead to draft now with what it has (Winquill marks the gaps [TO CONFIRM]). Drafting starts once Winquill's questions are answered, or when draft_now is true. Pass each answer with the question's number or words. Needs a Winquill account. Do not use for a new bid (use start_bid_draft).

Inputs: notes, answers, draft_id, draft_now, +3 more. Returns: status, tender, draftId, summary, +1 more

draft_bid_responseDraft a bid answerA
Read-only
Inspect

Use this when the user wants help writing part of a response to a public tender: a quality question answer, social value response, method statement, case study, company overview, cover letter or clarification question. Returns a drafting brief built from the tender's award criteria, word limits and the user's facts, so the draft answers what evaluators will score. Write the draft from the brief. Do not use for job applications, grant applications or private-sector sales proposals.

Inputs: section (required), notes, question, word_limit, +1 more. Returns: team, brief, found, credit, +2 more

find_companyFind a companyB
Read-only
Inspect

Finds a UK company on Companies House by name, for Winquill's setup.

Inputs: name (required).

finish_setupFinish setupC
Destructive
Inspect

Saves what Winquill's setup was told, making the workspace for someone without one, and finds the open tenders that fit.

Inputs: name (required), work (required), regions (required), size, +3 more.

get_automation_historyShow what automations didA
Read-only
Inspect

Use this when the user asks what Winquill's automations did lately: the last 10 things they did, newest first, for one automation or all of them. Needs a Winquill account and workspace.

Inputs: workspace, automation. Returns: link, history, library, summary, +4 more

get_automation_libraryShow the automations libraryA
Read-only
Inspect

Use this when the user wants to know which automations Winquill can run for them, before making one with add_automation. Returns each one in Winquill's library, what it does and whether the workspace has it already. Needs a Winquill account and workspace.

Inputs: workspace. Returns: link, history, library, summary, +4 more

get_bid_draftCheck on Winquill's bid draftA
Read-only
Inspect

Use this when the user asks how a bid Winquill is drafting is going, or wants to read it: its progress in steps and answers written, each question with its word count and Winquill's mark out of 5, what's left for the team to confirm, and the check of the whole bid. Give question to read that answer in full. Once it's ready, it gives a Word file link that works for an hour, and a link to the draft in Winquill. Needs a Winquill account. Example: {"tender_reference":"012345-2026"}

Inputs: draft_id, question, workspace, tender_reference. Returns: files, status, tender, draftId, +2 more

get_coverageShow Winquill's coverageA
Read-only
Inspect

Use this to know where Winquill looks: the countries and sources it reads, how many open, upcoming and awarded notices each holds, and when each was last read. Use it before telling the user a tender isn't published anywhere Winquill reads, or to say how fresh results are. Not for searching (use search_tenders). Example: {"country":"Canada"}

Inputs: country. Returns: asOf, covered, summary, countries

get_pipeline_statusGet pipeline statusA
Read-only
Inspect

Use this when the user asks how their team's bids are going, for a status report, or what is due: how many tenders are in each stage of their Winquill pipeline, which bids are running with their next step and due date, which tenders still need the bid or no-bid call, and which bids are waiting on a result. Needs a Winquill account and workspace. Do not use to find new tenders (use search_tenders) or for alerts from saved watches (use get_tender_updates).

Inputs: workspace. Returns: links, stages, running, summary, +3 more

get_tenda_settingsWinquill settingsA
Read-only
Inspect

Use this when the user asks which Winquill workspace ChatGPT uses, or which countries' tenders it shows: returns Winquill's settings in ChatGPT, the workspace (for someone in more than one) and the workspace's countries. Needs a Winquill account. Do not use for the company profile (use save_company_profile).

Inputs: no named parameters. Returns: layout, schema, values

get_tender_detailsExplain a tenderA
Read-only
Inspect

Use this when the user asks about one tender, framework or standing offer, by notice ID, buyer reference or from earlier results: the deadline, the portal to submit through, lots, value, conditions, award criteria and what the buyer wants, in plain English. It also reads the competition: who holds the work now, what the buyer paid before, how many bids it drew, and whether the tender is worth chasing. Not for finding tenders (use search_tenders). Example: {"tender_reference":"012345-2026"}

Inputs: tender_reference (required), more_references. Returns: lots, buyer, codes, found, +15 more

get_tender_updatesGet tender alertsAInspect

Use this when the user asks what's new from their Winquill watches: new matching tenders, pipeline notices, deadline changes, clarifications, cancellations and awards. Without since, it gives the updates not shown before and marks them seen. Agents that check on a schedule pass since, the nextSince from the answer before: it reads what was recorded after it, oldest first, and marks nothing. watch_id keeps to one watch. Needs a Winquill account. Not for searching (use search_tenders). Example: {"since":"eyJzZXEiOjQyfQ"}

Inputs: since, watch_id. Returns: more, credit, summary, updates, +1 more

list_automationsList automationsA
Read-only
Inspect

Use this when the user asks what Winquill does on its own for their team: the workspace's automations, each with its rules as sentences, whether it's on and what it last did, and the ones Winquill suggests. Needs a Winquill account and workspace. Not for making one (use add_automation) or what one did (use get_automation_history).

Inputs: workspace. Returns: link, history, library, summary, +4 more

list_watchesList my watchesA
Read-onlyIdempotent
Inspect

Use this when the user asks which Winquill watches they have, or to find the one to stop: each watch with its ID, what it watches for, its countries and whether it posts to Slack or Teams. Needs a Winquill account. Do not use for what the watches found (use get_tender_updates). Example: {}

Inputs: no named parameters. Returns: summary, watches

move_in_pipelineMove a tender in the pipelineA
DestructiveIdempotent
Inspect

Use this when the user wants to change where a tender stands in their team's Winquill pipeline: to Qualifying while they look into it, back to Watching, to Submitted, or to Won or Lost when the buyer announces the result. Moving to Bidding or No bid takes the bid or no-bid call (use record_bid_call). Needs a Winquill account and workspace. Do not use to take a tender off the pipeline (use remove_from_pipeline).

Inputs: stage (required), tender_reference (required), workspace. Returns: moved, stage, tender, summary, +1 more

open_bid_panelBid panelC
Read-only
Inspect

Opens the team's live bids beside a chat: each bid's steps and questions, what scores, and a way to work on one in the chat.

Inputs: path, workspace.

open_tendaWinquillC
Read-only
Inspect

Opens Winquill's own app from ChatGPT's sidebar: Today, the team's board, Find and each tender, with the bid call. The app moves between its pages itself.

Inputs: path, workspace.

record_bid_callRecord the bid callA
Destructive
Inspect

Use this when the user's team has decided whether to bid: records the bid or no-bid call, the team's answers to Winquill's five questions and the reason. A bid moves the tender to Bidding and plans a six-step sprint back from the deadline; a tender not in the pipeline is added first. Confirm the decision with the user before calling. Needs a Winquill account and a role that makes bid calls. Not for judging fit before the call (use assess_tender_fit). Example: {"tender_reference":"012345-2026","decision":"bid","answers":{"fit":"yes"}}

Inputs: decision (required), tender_reference (required), reason, answers, +1 more. Returns: stage, tender, summary, recorded, +1 more

record_portal_accountNote a portal accountA
DestructiveIdempotent
Inspect

Use this when the user says whether their company has an account on the e-tendering portal a tender is run on, where suppliers get the tender pack and bid, often after Winquill asked as a tender joined the pipeline: "yes, we have an EU-Supply account" or "no, we're not on Atamis yet". Notes it for the whole team, so Winquill stops asking about that portal. Give the tender's reference, or the portal's name or the key Winquill gave (portal.key). Needs a Winquill account and workspace. Do not use to sign in to a portal: Winquill never handles portal passwords.

Inputs: has_account (required), portal, workspace, tender_reference. Returns: tender, summary, recorded, workspace, +1 more

remove_from_pipelineTake a tender off the pipelineA
DestructiveIdempotent
Inspect

Use this when the user wants a tender taken off their team's Winquill pipeline, for good or until a change brings it back: "remove it until it gets a value". It deletes the tender's bid call, sprint and the files the team added; for one in Bidding, Submitted, Won or Lost the answer asks first, so confirm with the user and call again with confirmed. Needs a Winquill account and workspace. Not for moving a tender to another stage (use move_in_pipeline) or a no-bid call (use record_bid_call). Example: {"tender_reference":"012345-2026","return_when":"value"}

Inputs: tender_reference (required), confirmed, workspace, return_when. Returns: from, tender, removed, summary, +4 more

review_bid_draftCheck a bid answer before submittingA
Read-only
Inspect

Use this when the user has a draft answer for a public tender and wants it checked before submission, the way an evaluator would: word limit, every part of the question answered, specific evidence, firm commitments, no unfinished placeholders or empty superlatives, and what the section type needs (mobilisation, KPIs, measurable social value). Returns checks plus the tender's scoring criteria and a 0 to 5 rubric to score it against. Do not use to write a new answer (use draft_bid_response).

Inputs: draft (required), section (required), question, word_limit, +1 more. Returns: found, credit, review, tender, +1 more

rewrite_bid_answerHave Winquill rewrite an answerA
Destructive
Inspect

Use this when the user wants Winquill to rewrite one answer in a bid it drafted, e.g. "make Q3 shorter" or "use the Glasgow contract as the example in 2.1". Winquill rewrites it in the background, marks it again and says when it's done. A bid's first ten rewrites are included; after that each uses a little of the workspace's allowance. Needs a Winquill account. Do not use before the draft is ready.

Inputs: question (required), instruction (required), draft_id, workspace, +1 more. Returns: link, status, tender, draftId, +3 more

save_company_profileSave company profileA
DestructiveIdempotent
Inspect

Use this when the user wants Winquill to remember their business for searches, fit and readiness checks and drafting. Fill in only company facts the user has told you, leaving out anything unsure and any personal details, and show the user what you'll save so they can confirm or correct it first. Saves to their team's workspace and fills in more from Companies House (SAM.gov for a US company) and contracts the company has won. Needs a Winquill account. Not for personal profiles or CVs. Example: {"summary":"Office and school cleaning in Greater Manchester","company_number":"08123456"}

Inputs: staff, regions, summary, website, +15 more. Returns: saved, summary, workspace

search_contract_awardsSearch past awards and re-tendersA
Read-only
Inspect

Use this to find who won public contracts in the UK, Canada, the United States, Germany, France and the rest of the EU, what a buyer paid last time, and which contracts end soon and may be re-tendered. Searches the user's own countries unless they name one. Answers give the total, pass nextCursor back as cursor for more, and summarise says who won most across every match. Not for tenders open now (use search_tenders) or a public body's total spending. Example: {"buyer":"Leeds City Council","query":"cleaning","summarise":"supplier"}

Inputs: buyer, codes, limit, query, +8 more. Returns: total, credit, results, summary, +3 more

search_mentionsFind a tender or person to mentionA
Read-only
Inspect

Finds the team's tenders and people by name, for @ mentions in ChatGPT.

Inputs: query (required). Returns: items

search_tendersSearch public tendersA
Read-only
Inspect

Use this to find public sector contracts to bid for in the UK, Canada, the United States, Germany, France and the rest of the EU: open tenders, frameworks and upcoming notices from any public buyer. Searches the user's own countries unless they name one; get_coverage lists every source and when it was last read. Answers give the total; pass nextCursor back as cursor for more. Not for past winners (use search_contract_awards) or jobs. Example: {"query":"school cleaning","region":"North West","closing_within_days":30}

Inputs: sort, buyer, codes, limit, +14 more. Returns: asOf, note, total, credit, +5 more

set_up_tendaSet up WinquillA
Read-only
Inspect

Use this when the user wants to set Winquill up for their company, or has just added Winquill and has no workspace yet: shows a short form in the chat for the company, where it works and the work it does, then how many open tenders fit it now. Needs a Winquill account. Do not use to change one fact the user names, such as a certification (use save_company_profile).

Inputs: workspace.

share_tenderShare a tenderA
Read-only
Inspect

Use this when the user wants to share a tender or send someone its link. Returns a link anyone can open without signing in: it shows what the public notice says, and chat apps preview it with the tender's name, value and closing date. Give the link as it is. Nothing about the user or their workspace is in the link or on the page.

Inputs: tender_reference (required). Returns: link, found, credit, shared, +2 more

start_bid_draftHave Winquill draft the bidA
Destructive
Inspect

Use this when the user wants Winquill to write a whole bid for their team: it asks a few questions, drafts every answer from the company's evidence, then marks and revises them. Relay Winquill's questions as they are. A whole bid uses one of the month's full bids, so first call it without confirmed, tell the user how many are left and offer to write it here with draft_bid_response, which uses none; call again with confirmed only if they choose Winquill. notify says where to hear when it's ready. Needs a Winquill account and workspace. Example: {"tender_reference":"012345-2026"}

Inputs: tender_reference (required), notify, confirmed, workspace, +1 more. Returns: status, tender, confirm, draftId, +4 more

stop_watchStop a watchA
DestructiveIdempotent
Inspect

Use this when the user wants to stop one of their Winquill watches, by the watchId that watch_tenders or list_watches gave. It finds nothing new after that; what it already found still shows in get_tender_updates. Needs a Winquill account. Example: {"watch_id":"wch_abc123"}

Inputs: watch_id (required). Returns: stopped, summary, watchId

tenda_changesCheck for changesC
Read-only
Inspect

Says when the team's work in a workspace last changed, for Winquill's app to keep its page up to date.

Inputs: workspace (required), tender_reference.

turn_off_automationTurn off an automationA
Idempotent
Inspect

Use this when the user wants one of the workspace's automations to stop. It stops running and keeps its rules and history, so it can be turned on again. Needs a Winquill account; owners, admins and bid leads turn them off.

Inputs: automation (required), workspace. Returns: link, history, library, summary, +4 more

turn_on_automationTurn on an automationA
DestructiveIdempotent
Inspect

Use this only after you have read an automation's rules back to the user in plain words and they said yes to turning it on. From then on it runs as the user, outside quiet hours, and acts on the team's pipeline as its rules say. Automations never submit a bid, send anything to a buyer, decline a tender, email anyone outside the team or change who is in the workspace. Needs a Winquill account; owners, admins and bid leads turn them on. Not for turning one off (use turn_off_automation).

Inputs: automation (required), workspace. Returns: link, history, library, summary, +4 more

update_bid_sprintUpdate the bid sprintA
DestructiveIdempotent
Inspect

Use this when the user says a step of a bid their team is running is done, or not done after all: decode the pack, assign questions, draft answers, review and score, final checks or submit. Ticks it off with who did it and when, and says what is next and when it is due. Ticking submit moves the tender to Submitted. Needs a Winquill account and a bid sprint, which starts with a call to bid (record_bid_call). Do not use to write or check answers (use draft_bid_response or review_bid_draft).

Inputs: step (required), tender_reference (required), done, workspace. Returns: stage, tender, summary, updated, +1 more

update_tenda_settingsChange Winquill settingsA
Destructive
Inspect

Use this when the user wants ChatGPT to use another of their Winquill workspaces, or to show tenders from another country or stop: set "workspace" to the workspace's name, or a country's key from get_tenda_settings (such as "us") to true or false. The workspace's home country stays on. Owners and admins change countries. Needs a Winquill account.

Inputs: set (required). Returns: values

watch_tendersWatch for tendersAInspect

Use this when the user wants alerts for new tenders or upcoming notices that match a search, or for changes to one tender they follow (clarifications, new deadlines, the award). Saves a watch and gives its watchId: matches show in get_tender_updates and, with notify, in the workspace's Slack or Teams channels that get changes. Needs a Winquill account. Not for seeing the user's watches (use list_watches) or stopping one (use stop_watch). Example: {"query":"office cleaning","include_upcoming":true}

Inputs: query, notify, region, country, +3 more. Returns: found, credit, notify, created, +5 more

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      C
      maintenance
      Enables AI agents to find, score, and monitor government contract opportunities across UK, EU, and US with AI-powered relevance scoring.
      2
      64 npm
      1
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables searching and analyzing government tenders, contract awards, and pre-tender pipelines from 21 official sources, with tools for tender search, award intelligence, and detailed notice retrieval.
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources