MCP servers › ai.eshmere › tenda

MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23

ai.eshmere/tenda

Public tenders and contract awards in the UK, US, Canada and EU, and help preparing bids. — the publisher's description

1 of 2 record checks metRead-only · tools listed 2026-10-23Pricing: usage-based · AI-classifiedversion 0.1.0streamable HTTP36 tools

Summary

ai.eshmere/tenda is a remote MCP server listed in the official MCP registry at version 0.1.0. On 2026-10-23 ProtocolProbe connected to it in read-only mode and read its inventory: 36 tools, 2 resources and 0 prompts.

Record checks

1 of 2 record checks met · 7 do not apply

met: Registry entry is active and says how to run it
not met: Source repository link opens
not applicable: Repository is not archived
not applicable: Code pushed to the repository in the 90 days before our check
not applicable: Repository publishes a security policy (SECURITY.md)
not applicable: Package names its licence with a standard (SPDX) identifier
not applicable: The version the registry lists can be installed and is not withdrawn
not applicable: npm package carries build provenance (attestation)
not applicable: No known critical or high advisory in the package or its dependencies

Not ranked by downloads: a remote server publishes no download figure
Not ranked by stars: no public GitHub repository

From public records, not a safety rating. Each check with its reason · Is it safe to install?

Key facts

Runs: remote (hosted by the publisher)
Transport: streamable HTTP
Sign-in: none needed to open a session
Tools: 36
Described as changing data: 19 of 36 toolsAI-classified
Mainly works on: files and code on the machine it runs on; accounts and data in outside web servicesAI-classified
Pricing: usage-basedAI-classified
Last tested: 2026-10-23

Add to your client

Observed fact

This server accepted a session without any credential and lists 16 tools whose name or declaration suggests they change data (stop_watch, add_tender_documents, save_company_profile, add_to_pipeline, record_portal_account and 11 more). That is our reading of the names; we did not call them. Source: our connection, 2026-10-23.

Worth knowing before you connect it

19 tools are described as changing something (draft_bid_response, watch_tenders, stop_watch, …): our AI model's reading of the descriptions, not something we tested, and the server opened a session without any credential. We did not call them.

Each line comes from a section below, with its source and date.

How fresh this is

Live-tested: yes, a real session (not a text-only review)
Last tested: 2026-10-23
Mode: read-only (no tool calls)
Latest version: 0.1.0, published 2026-10-09 (registry, as of the 2026-10-23 snapshot)
First listed version: 2026-10-09 (earliest version still in the registry; older removed versions would be earlier)
Registry data: snapshot 2026-10-23
Package and repository: checked 2026-10-22
Engine: mcp-runtime-engine@0.1.0 · sdk@1.32.0

Changes since the last refresh

New in the registry: not in the list of 2026-10-04, listed on 2026-10-23 with version 0.1.0 (published 2026-10-09).

Source: the official MCP Registry list on 2026-10-04 and on 2026-10-23.

What it is

What does this server offer?

Observed inventory

36tools

2resources

0prompts

What it mainly works on, as our AI model read its tool descriptions: files and code on the machine it runs on; accounts and data in outside web services.

19 of 36 tools are described as changing something (creating, editing, deleting, sending or running). For 2 the reading was uncertain, so no mark is shown.

search_tenderson 24 other serversreads or searches
“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.”
Publisher declares: read-only yes · destructive no · open-world no
18 inputs
- querystring“What the buyer is buying, in the user's words, e.g.”
- countrystring“The country to look in, when the user names one, e.g.”
- regionstring“Where the work or delivery happens: a UK nation or English region, e.g.”
- buyer_typestring“Kind of public buyer, e.g.”
- contract_typestring“What is being bought, e.g.”
- stagestring“"open" for tenders taking bids now, "upcoming" for pipeline and preliminary market engagement notices about future tenders.”
- procedurestring“How the buyer is buying, e.g.”
- suitable_forstring“Only notices the buyer marked as suitable for small and medium-sized enterprises or for voluntary, community and social enterprises.”
- min_value_gbpinteger“Lowest estimated contract value in the country's own currency (pounds for the UK, Canadian dollars for Canada, US dollars for the US, euros for Germany, France…”
- max_value_gbpinteger“Highest estimated contract value in the country's own currency (pounds for the UK, Canadian dollars for Canada, US dollars for the US, euros for Germany, Franc…”
- closing_within_daysinteger“Only tenders closing within this many days, e.g.”
- buyerstring“Only tenders from a buyer whose name holds these words, e.g.”
- codesarray“Only tenders with one of these classification codes, or a code under one: CPV in the UK and EU, e.g.”
- published_sincestring“Only tenders published on or after this date, e.g.”
- sortstring“"best", the default: best fit first for a user with a saved company profile, otherwise the closest match; "closing": soonest deadline first; "newest": latest p…”
- limitinteger“How many to show, up to 50.”
- cursorstring“The nextCursor from an earlier answer, with the same search, for its next page.”
- detailstring“"short" for just each result's IDs, title, buyer, value, dates and link, e.g.”
get_tender_detailson 2 other serversreads or searches
“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, …”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
- tender_referencestringrequired“The notice ID, procurement identifier, solicitation number or the buyer's own reference, e.g.”
search_contract_awardson 1 other serverreads or searches
“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-tendere…”
Publisher declares: read-only yes · destructive no · open-world no
12 inputs
- querystring“What the contract covers, e.g.”
- buyerstring“Public body that awarded the contract, e.g.”
- supplierstring“Company that holds or won the contract, e.g.”
- countrystring“The country to look in, when the user names one, e.g.”
- regionstring“Where the work or delivery happens: a UK nation or English region, e.g.”
- ending_within_monthsinteger“Only contracts ending within this many months, e.g.”
- codesarray“Only contracts with one of these classification codes, or a code under one: CPV in the UK and EU, e.g.”
- awarded_sincestring“Only contracts awarded on or after this date, e.g.”
- limitinteger“How many to show, up to 50.”
- cursorstring“The nextCursor from an earlier answer, with the same search, for its next page.”
- detailstring“"short" for just each result's IDs, title, buyer, value, dates and link, e.g.”
- summarisestring“Adds overview, a summary of every matching award, not just this page: "buyer" for who wins a buyer's contracts, "supplier" for what a supplier wins and from wh…”
assess_tender_fitreads or searches
“Use this when the user asks whether their business should bid for a public contract, or which open tenders suit them best.”
Publisher declares: read-only yes · destructive no · open-world no
5 inputs
- tender_referencestring“The notice ID, procurement identifier, solicitation number or the buyer's own reference, e.g.”
- company_summarystring“What the company does, its size, turnover, certifications, insurance, where it works and past contracts, in the user's words, e.g.”
- business_sizestring“The company's size, e.g.”
- querystring“When ranking without a tender_reference: the kind of work to look for, e.g.”
- countrystring“The country to look in, when the user names one, e.g.”
check_bid_readinessreads or searches
“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 Cy…”
Publisher declares: read-only yes · destructive no · open-world no
4 inputs
- tender_referencestring“Optional tender to check against, e.g.”
- sectorstring“The kind of work the company bids for, e.g.”
- documents_heldarray“Documents and certifications the user says they already have, e.g.”
- countrystring“The country whose rules to check against, when the user names one, e.g.”
draft_bid_responsegenerates contentdescribed as changing data
“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 clar…”
Publisher declares: read-only yes · destructive no · open-world no
5 inputs, 1 required
- tender_referencestring“The tender being answered, e.g.”
- sectionstringrequired“Which part of the bid to draft, e.g.”
- word_limitinteger“The buyer's word limit for this answer, e.g.”
- questionstring“The buyer's question, word for word, when the user has it.”
- notesstring“Facts the draft should use, e.g.”
review_bid_draftreads or searches
“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, f…”
Publisher declares: read-only yes · destructive no · open-world no
5 inputs, 2 required
- draftstringrequired“The draft answer text.”
- sectionstringrequired“What the draft is, e.g.”
- tender_referencestring“The notice ID, procurement identifier, solicitation number or the buyer's own reference, e.g.”
- word_limitinteger“The buyer's word limit for this answer.”
- questionstring“The buyer's question, word for word, so Tenda can check every part is answered.”
watch_tenderscreates or changes datadescribed as changing data
“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).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
7 inputs
- querystring“What to watch for, e.g.”
- countrystring“The country to look in, when the user names one, e.g.”
- regionstring“Where the work or delivery happens: a UK nation or English region, e.g.”
- buyer_typestring“Kind of public buyer, e.g.”
- include_upcomingboolean“Also alert on pipeline and preliminary market engagement notices, to hear about work before it is tendered.”
- tender_referencestring“Watch one tender for clarifications, deadline changes and the award instead of a search, e.g.”
- notifyarray“Also post what the watch finds to the user's workspace's Slack or Teams channels, where they get changes.”
list_watcheson 21 other serversreads or searches
“Use this when the user asks which Tenda 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.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
stop_watchon 2 other serversdeletesdescribed as changing data
“Use this when the user wants to stop one of their Tenda watches, by the watchId that watch_tenders or list_watches gave.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
1 input, 1 required
- watch_idstringrequired“The watch to stop, by the id watch_tenders or list_watches gave.”
get_tender_updatesreads or searches
“Use this when the user asks what's new from their Tenda watches: new matching tenders, pipeline notices, deadline changes, clarifications, cancellations and awards.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
2 inputs
- sincestring“The nextSince from an earlier answer, for the updates recorded after it.”
- watch_idstring“Only this watch's updates, by the id watch_tenders gave.”
add_tender_documentsdescribed as changing data
“Use this when the user shares text from a tender's documents, or wants Tenda to read the files the buyer published with the notice (read_published, signed in).”
Publisher declares: read-only no · destructive yes · open-world yes
5 inputs, 1 required
- tender_referencestringrequired“The notice ID, procurement identifier, solicitation number or the buyer's own reference, e.g.”
- textstring“The document text the user shared, not a file link: an invitation to tender, selection questionnaire, specification or instructions to bidders.”
- titlestring“The document name, e.g.”
- read_publishedboolean“true to have Tenda fetch and read the files the buyer published with the notice, up to 8 (PDF, Word, Excel, web pages and ZIPs of them).”
- workspacestring“The Tenda workspace to use, by name, when the user is in more than one, e.g.”

Show 24 more tools

save_company_profilecreates or changes datadescribed as changing data
“Use this when the user wants Tenda to remember their business for searches, fit and readiness checks and drafting.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world yes
16 inputs, 1 required
- summarystringrequired“What the company does, who for and where, in a few sentences, e.g.”
- company_namestring“The company's name, e.g.”
- company_numberstring“The Companies House number, e.g.”
- websitestring“The company's website, e.g.”
- business_sizestring“The company's size, e.g.”
- staffinteger“How many people work for the company.”
- turnover_gbpnumber“Annual turnover in the company's home currency (pounds for a UK company, Canadian dollars for a Canadian one), e.g.”
- largest_contract_gbpnumber“The largest contract, a year, the company would take on, in its home currency.”
- regionsarray“Where the company works, e.g.”
- nationwideboolean“True when the company works anywhere in its country.”
- certificationsarray“Certifications and accreditations it holds, e.g.”
- public_liability_gbpnumber“Public liability (in Canada, commercial general liability) cover in the company's home currency, e.g.”
- employers_liability_gbpnumber“Employer's liability cover in the company's home currency, e.g.”
- professional_indemnity_gbpnumber“Professional indemnity cover in the company's home currency.”
- buyer_typesarray“Kinds of public buyer the company has worked for, e.g.”
- workspacestring“The Tenda workspace to use, by name, when the user is in more than one, e.g.”
get_pipeline_statuson 2 other serversreads or searches
“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 Tenda pipeline, which bids are running with their next st…”
Publisher declares: read-only yes · destructive no · open-world no
1 input
- workspacestring“The Tenda workspace to use, by name, when the user is in more than one, e.g.”
add_to_pipelinecreates or changes datadescribed as changing data
“Use this when the user wants to save a tender to their team's Tenda pipeline to consider bidding, e.g.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
3 inputs, 1 required
- tender_referencestringrequired“The notice ID, procurement identifier, solicitation number or the buyer's own reference, e.g.”
- more_referencesarray“More tenders to add at the same time, by the same kind of reference, when the user asks for several, e.g.”
- workspacestring“The Tenda workspace to use, by name, when the user is in more than one, e.g.”
record_portal_accountcreates or changes datadescribed as changing data
“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 Tenda asked as a tender joined …”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
4 inputs, 1 required
- has_accountbooleanrequired“Whether the company has an account on the portal.”
- tender_referencestring“The notice ID, procurement identifier, solicitation number or the buyer's own reference, e.g.”
- portalstring“The portal, e.g.”
- workspacestring“The Tenda workspace to use, by name, when the user is in more than one, e.g.”
record_bid_callcreates or changes datadescribed as changing data
“Use this when the user's team has decided whether to bid: records the bid or no-bid call, the team's answers to Tenda's five questions and the reason.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
5 inputs, 2 required
- tender_referencestringrequired“The notice ID, procurement identifier, solicitation number or the buyer's own reference, e.g.”
- decisionstringrequired“"bid" when the team will bid, "no_bid" when it will not.”
- answersobject“The team's answers to Tenda's five questions, each "yes", "unsure" or "no": fit (is this work we do well), eligibility (do we meet every must-have), capacity (…”
- reasonstring“Why, in the user's words, for the team to read later.”
- workspacestring“The Tenda workspace to use, by name, when the user is in more than one, e.g.”
update_bid_sprintcreates or changes datadescribed as changing data
“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.”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
4 inputs, 2 required
- tender_referencestringrequired“The notice ID, procurement identifier, solicitation number or the buyer's own reference, e.g.”
- stepstringrequired“The step: "decode" (read the tender pack), "assign" (give each question an owner), "draft" (write the answers), "review" (score them), "checks" (final checks) …”
- doneboolean“false to reopen a step ticked off by mistake.”
- workspacestring“The Tenda workspace to use, by name, when the user is in more than one, e.g.”
assign_taskon 4 other serverscreates or changes datadescribed as changing data
“Use this when the user gives work on a team bid to someone, or takes it on: "give the Bristol bid call to Sam".”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
4 inputs, 2 required
- tender_referencestringrequired“The notice ID, procurement identifier, solicitation number or the buyer's own reference, e.g.”
- personstringrequired“Who gets it: their name as the team knows them, e.g.”
- taskstring“The work: "call" (the bid or no-bid call), or a sprint step: "decode", "assign", "draft", "review", "checks" or "submit".”
- workspacestring“The Tenda workspace to use, by name, when the user is in more than one, e.g.”
move_in_pipelinecreates or changes datadescribed as changing data
“Use this when the user wants to change where a tender stands in their team's Tenda pipeline: to Qualifying while they look into it, back to Watching, to Submitted, or to Won or Lost when the buyer an…”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
3 inputs, 2 required
- tender_referencestringrequired“The notice ID, procurement identifier, solicitation number or the buyer's own reference, e.g.”
- stagestringrequired“Where the tender goes: "watching", "qualifying", "bidding", "submitted", "won", "lost" or "no_bid".”
- workspacestring“The Tenda workspace to use, by name, when the user is in more than one, e.g.”
choose_alertscreates or changes datadescribed as changing data
“Use this when the user wants to change which Slack and Teams channels get Tenda's alerts, or asks where they go: "stop the morning summary in Slack".”
Publisher declares: read-only no · destructive yes · idempotent yes · open-world no
6 inputs
- appstring“"slack" or "teams" for that app's channels.”
- channelstring“One channel, by its name: e.g.”
- sendarray“Alerts to turn on in those channels: "new_tenders" (new tenders that fit the company), "changes" (changes to tenders in the pipeline), "morning_summary" (the w…”
- stoparray“Alerts to turn off in those channels: "new_tenders" (new tenders that fit the company), "changes" (changes to tenders in the pipeline), "morning_summary" (the …”
- onlyboolean“true when what's sent here should go only here: every other channel stops getting it.”
- workspacestring“The Tenda workspace to use, by name, when the user is in more than one, e.g.”
start_bid_draftgenerates contentdescribed as changing data
“Use this when the user wants Tenda 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.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world yes
5 inputs, 1 required
- tender_referencestringrequired“The notice ID, procurement identifier, solicitation number or the buyer's own reference, e.g.”
- questions_textstring“The buyer's questions, or the invitation to tender's text, as the user shared it, including the text of files they attached.”
- confirmedboolean“true once the user, told it uses one of this month's full bids, chose Tenda's drafting over writing it here answer by answer with draft_bid_response.”
- notifyarray“Where Tenda says when the draft is ready, e.g.”
- workspacestring“The Tenda workspace to use, by name, when the user is in more than one, e.g.”
continue_bid_draftgenerates contentdescribed as changing data
“Use this to carry on a bid draft Tenda started with start_bid_draft: give it the buyer's questions it asked for, the team's answers to the questions Tenda asked, or the go-ahead to draft now with wha…”
Publisher declares: read-only no · destructive yes · idempotent no · open-world yes
7 inputs
- draft_idstring“The draft's ID, from start_bid_draft.”
- tender_referencestring“The notice ID, procurement identifier, solicitation number or the buyer's own reference, e.g.”
- questions_textstring“The buyer's questions, when Tenda asked for them.”
- answersarray“The team's answers to Tenda's questions.”
- notesstring“Anything else the team wants Tenda to use in the bid.”
- draft_nowboolean“true to start drafting now, with any of Tenda's questions unanswered.”
- workspacestring“The Tenda workspace to use, by name, when the user is in more than one, e.g.”
get_bid_draftreads or searches
“Use this when the user asks how a bid Tenda is drafting is going, or wants to read it: its progress in steps and answers written, each question with its word count and Tenda's mark out of 5, what's l…”
Publisher declares: read-only yes · destructive no · open-world no
4 inputs
- draft_idstring“The draft's ID, from start_bid_draft.”
- tender_referencestring“The notice ID, procurement identifier, solicitation number or the buyer's own reference, e.g.”
- questionstring“One answer to read in full, by the buyer's number, e.g.”
- workspacestring“The Tenda workspace to use, by name, when the user is in more than one, e.g.”
rewrite_bid_answergenerates contentdescribed as changing data
“Use this when the user wants Tenda to rewrite one answer in a bid it drafted, e.g.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
5 inputs, 2 required
- draft_idstring“The draft's ID, from start_bid_draft.”
- tender_referencestring“The notice ID, procurement identifier, solicitation number or the buyer's own reference, e.g.”
- questionstringrequired“The answer to rewrite, by the buyer's number, e.g.”
- instructionstringrequired“What to change, in the user's words.”
- workspacestring“The Tenda workspace to use, by name, when the user is in more than one, e.g.”
add_winning_bidcreates or changes datadescribed as changing data
“Use this when the user shares a bid their company won, for Tenda to learn from, e.g.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
3 inputs, 1 required
- textstringrequired“The winning bid's text: its answers, as the user shared them.”
- titlestring“What it was, e.g.”
- workspacestring“The Tenda workspace to use, by name, when the user is in more than one, e.g.”
get_coverageon 45 other serversreads or searches
“Use this to know where Tenda looks: the countries and sources it reads, how many open, upcoming and awarded notices each holds, and when each was last read.”
Publisher declares: read-only yes · destructive no · open-world no
1 input
- countrystring“One country, e.g.”
open_tendacontrols a browser or desktop
“Opens Tenda's own app from ChatGPT's sidebar: Today, the team's board, Find and each tender, with the bid call.”
Publisher declares: read-only yes · destructive no · open-world no
2 inputs
- pathstring
- workspacestring
open_bid_panelcontrols a browser or desktop
“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.”
Publisher declares: read-only yes · destructive no · open-world no
2 inputs
- pathstring
- workspacestring
tenda_changesreads or searches
“Says when the team's work in a workspace last changed, for Tenda's app to keep its page up to date.”
Publisher declares: read-only yes · destructive no · open-world no
2 inputs, 1 required
- workspacestringrequired
- tender_referencestring
search_mentionson 5 other serversreads or searches
“Finds the team's tenders and people by name, for @ mentions in ChatGPT.”
Publisher declares: read-only yes · destructive no · open-world no
1 input, 1 required
- querystringrequired
get_tenda_settingsreads or searches
“Use this when the user asks which Tenda workspace ChatGPT uses, or which countries' tenders it shows: returns Tenda's settings in ChatGPT, the workspace (for someone in more than one) and the workspa…”
Publisher declares: read-only yes · destructive no · open-world no
Takes no inputs.
update_tenda_settingscreates or changes datadescribed as changing data
“Use this when the user wants ChatGPT to use another of their Tenda workspaces, or to show tenders from another country or stop: set "workspace" to the workspace's name, or a country's key from get_te…”
Publisher declares: read-only no · destructive yes · open-world no
1 input, 1 required
- setobjectrequired
set_up_tendacreates or changes datadescribed as changing data
“Use this when the user wants to set Tenda up for their company, or has just added Tenda and has no workspace yet: shows a short form in the chat for the company, where it works and the work it does, …”
Publisher declares: read-only yes · destructive no · open-world no
1 input
- workspacestring“The Tenda workspace to set up, by name, when the user is in more than one, e.g.”
find_companyon 9 other serversreads or searches
“Finds a UK company on Companies House by name, for Tenda's setup.”
Publisher declares: read-only yes · destructive no · open-world yes
1 input, 1 required
- namestringrequired
finish_setupcreates or changes datadescribed as changing data
“Saves what Tenda's setup was told, making the workspace for someone without one, and finds the open tenders that fit.”
Publisher declares: read-only no · destructive yes · open-world yes
7 inputs, 3 required
- workspacestring
- marketstring
- namestringrequired
- company_numberstring
- regionsarrayrequired
- workarrayrequired
- sizestring

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-23.

How well are its tools described?

Features #4 and #5

How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.

Descriptions

AI reading of each description

Says what the tool does: 100% of 36 tools
Says what it returns: 100% of 17 tools
States limits, defaults or errors: 100% of 2 tools
Says when to use it: 100% of 36 tools
Items covered per tool: 4.0 of 4 on average

Counted from the listing

Parameters with a description: 90% of 153
Tools with a description: 100% of 36
Typical description length: 410 characters

The tool set

Counted from the listing

Tools: 36
Size of the list: about 25,869 tokens for an agent to load (characters ÷ 4)
Naming: 36 of 36 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 36 of 36 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.

How do I add it to my client?

Config from the registry entry

From the remote endpoint (Streamable HTTP)

We connected to this URL on 2026-10-23 (a read-only session: no tool was called).

Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.

Claude Desktop or claude.ai

Settings → Connectors → Add custom connector, then paste:
https://mcp.tenda.eshmere.ai/mcp

Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "tenda": {
      "url": "https://mcp.tenda.eshmere.ai/mcp"
    }
  }
}

VS Code · .vscode/mcp.json

{
  "servers": {
    "tenda": {
      "type": "http",
      "url": "https://mcp.tenda.eshmere.ai/mcp"
    }
  }
}

VS Code (command line) · Bash or zsh terminal (macOS, Linux)

code --add-mcp '{"name":"tenda","type":"http","url":"https://mcp.tenda.eshmere.ai/mcp"}'

Claude Code

claude mcp add --transport http tenda https://mcp.tenda.eshmere.ai/mcp

Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+

npx @modelcontextprotocol/inspector@2.11.0 --server-url https://mcp.tenda.eshmere.ai/mcp --transport http

The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.

Does the registry listing match what we found?

Feature #6

The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.

Registry says	We found	Result	Source · date
Remote endpoint mcp.tenda.eshmere.ai/mcp	Session opened	matches	our test · 2026-10-23
No credential declared as required	Opened a session without any credential	matches	our test · 2026-10-23

Choosing

Record checks

Public records · not a safety rating

1 of 2 record checks met · 7 do not apply

Not ranked by downloads: a remote server publishes no download figure
Not ranked by stars: no public GitHub repository

MetRegistry entry is active and says how to run itActive, with a package or a remote address.
Not metSource repository link opensThe registry entry gives no repository link.
Does not applyRepository is not archivedNo public GitHub repository to read.
Does not applyCode pushed to the repository in the 90 days before our checkNo public GitHub repository to read.
Does not applyRepository publishes a security policy (SECURITY.md)No public GitHub repository to read.
Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.

Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-22. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating. How each check works · Leaderboards

Common questions about ai.eshmere/tenda

Answered from the data above

Is ai.eshmere/tenda safe to install?

We do not rate servers as safe or unsafe. 1 of its 2 applicable record checks are met (facts from public records, each listed on this page). What the records show: 19 of its tools describe changing data (our AI model's reading of the descriptions). These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.

Is ai.eshmere/tenda free to use?

Its website (tenda.eshmere.ai/) describes a usage-based pricing model. This is an AI-classified reading of the page on 2026-10-23, so check the page itself before relying on it.

Does ai.eshmere/tenda need an API key or sign-in?

It opened a session without any credential on 2026-10-23. The registry entry declares no required credential; no declaration is not a guarantee.

Has ai.eshmere/tenda been security tested?

Partly. 4 of the 15 checks that apply to it were exercised. It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security verdict is published before verification.

What can ai.eshmere/tenda do?

It lists 36 tools. In our AI model's reading of their descriptions (two runs had to agree, nobody checked it by hand), they include tools that read or search, create or change data, delete, control a browser or desktop and generate content. We did not call any tool, so this describes the text, not the behaviour.

Can ai.eshmere/tenda change or delete data?

19 of its tools say in their description that they create, edit, delete, send or run something (our AI model's reading). We did not call any tool, so we cannot say what actually happens.

Found this page useful?

Anonymous · no sign-in

A quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.

Compare with another server

Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.

Security testing

What did we test, and what did we leave out?

18 checks · features #1, #2

Open without sign-in

It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security score is given; a check we did not run is never counted as passed.

The 18 checks at a glanceour test · 2026-10-23

Inventory: exercised
Hidden instructions: exercised
Real execution: not run · our policy
Secret leak: not run · nothing to check it against
Internal addresses: not run · our policy
Unconfirmed changes: not run · our policy
Bad input: not run · our policy
Model requests: not run · nothing to check it against
Sensitive questions: not run · nothing to check it against
Folder boundary: not run · our policy
Log leaks: not run · nothing to check it against
Hidden content: exercised
Fake assistant turns: not applicable
Token passthrough: not applicable
Token audience: not applicable
Sign-in redirect: not run · our policy
Consent handling: not testable from outside
Sign-in metadata: exercised

4 exercised11 not run (reason given)3 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 4 of the 15 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.

Exercised · 4

1Inventory
tool-listReads the declared tools, resources and prompts.exercised
2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised
12Hidden content
audience-hidingChecks resources that hide content from the user.exercised
18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.exercised

Not run, with the reason · 11

3Real execution
real-executionCalls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy
17Consent handling
confused-deputyChecks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside

Does not apply to this server · 3

13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable
14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable
15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable

Source: our own test, 2026-10-23, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.

What happened during the test?

Feature #8

The steps in order, as the test record holds them.

0 msStarted a read-only session with the server's remote endpoint
1,110 msConnected after 0 redirects. No credential was sent or needed.
Read the inventory: 36 tools, 2 resources, 0 prompts.
6,049 msFinished: 4 checks exercised.

Reference

How is it classified?

18 fields

One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.

TopicAI-classified

no value

No value: the two AI models (Gemini and Claude) disagreed, so neither answer is shown.

Pricing modelAI-classified

usage-based

read from tenda.eshmere.ai/ · 2026-10-23

“get started free → watch the film 0:58”

Programming language

does not apply

no existing GitHub repository (server declares no repository link, so there is nothing to fetch)

Hosting type

remote (hosted by the publisher)

registry · 2026-10-23

MCP capability

experimental, resources, tools, extensions

our test · 2026-10-23

Transport

streamable HTTP

registry · 2026-10-23

Required credentials

none declared

registry · no declaration is not a guarantee

Package registry

does not apply

remote-only server: no package is shipped, so there is no package registry

Freshness

0–30 days

registry updatedAt · 2026-10-23

Lifecycle status

active

registry · 2026-10-23

License class

does not apply

remote-only server: ships no package, so there is nothing to look up in a package registry

Integrity hash

does not apply

remote-only server: ships no package, so there is nothing to look up in a package registry

Signature / provenance

does not apply

remote-only server: ships no package, so there is nothing to look up in a package registry

Dependency advisories

does not apply

ships no package, so there are no dependencies to audit

Popularity

does not apply

remote-only server: ships no package, so there is nothing to look up in a package registry

Publisher signals

not stated

no readable GitHub owner to describe

Maintenance

does not apply

server declares no repository link, so there is nothing to fetch

Environment

the publisher's infrastructure

where it runs, from the hosting type

“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.

Cite or correct this page

Sources and corrections

Suggested citation

ProtocolProbe. “ai.eshmere/tenda: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/ai.eshmere/tenda

Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.

As JSON: this record in the API · API documentation.

Badge for your README

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/ai.eshmere/tenda)](https://protocolprobe.com/mcp/servers/ai.eshmere/tenda)

It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.

Something wrong, or is this yours?

If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.

Write to hello@protocolprobe.com · corrections log · methodology