Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Vinktar

REMOTE · MCP.VINKTAR.COM

Error tracking for small teams and their coding agents.

Available components

0 this week 94 Trust /100

Last scanned (16 hours ago)

Scores higher than 99% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Monitoring and Observability

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security97
Transport & Reachability100
Schema Quality & AI Usability73
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 11394 tokens (~325/item across 35 items; 31 tools + 4 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage97
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 90% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 33 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 13 Nov 26 0
    • Tool “add_panel” rewrote its description, which is the text the model reads security
    • “add_panel” reworded the description of “chart” cosmetic
    • “update_panel” reworded the description of “chart” cosmetic
  • 11 Nov 26 +1
    • Stability: 0.97 → pass security
  • 10 Nov 26 +1
    • Stability: fail → 0.97 functional
  • 9 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 84 to 87.

  • 8 Nov 26 −1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 84.

  • 7 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 84 to 87.

  • 6 Nov 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 5 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 77 to 80.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://mcp.vinktar.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=vinktar.com CN=YE1,O=Let's Encrypt,C=US 15 Nov 2026 13 Feb 2027 ECDSA 256 ECDSA-SHA384 56e03ee7c57634da641d58381abf2751c18
SANs: in.vinktar.com, mcp.vinktar.com, vinktar.com, www.vinktar.com
CN=YE1,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 5ddd70dd31f801c85c186a7a04b80afe
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of mcp.vinktar.com. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
com. DS published 19718 13 Verified
vinktar.com. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication Enforced and verified

The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.

Result Enforced and verified
Enforced On tool calls
HTTP status 200

WWW-Authenticate challenge Bearer resource_metadata="https://mcp.vinktar.com/.well-known/oauth-protected-resource/mcp", scope="mcp:read mcp:write"

Bearer resource_metadata="https://mcp.vinktar.com/.well-known/oauth-protected-resource/mcp", scope="mcp:read mcp:write"
Header Value
strict-transport-security max-age=63072000; includeSubDomains; preload
x-content-type-options nosniff
x-frame-options DENY
referrer-policy no-referrer, strict-origin-when-cross-origin

Protected resource metadata

Document https://mcp.vinktar.com/.well-known/oauth-protected-resource/mcp
Retrieved Yes
Resource https://mcp.vinktar.com/mcp
Authorisation server https://mcp.vinktar.com

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://mcp.vinktar.com/mcp Verified 200
http (plaintext) http://mcp.vinktar.com/mcp HTTPS enforced 301 https://mcp.vinktar.com/mcp
MCP tools · 31 exposed · ~9,998 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
add_panel ~1,144

Add a panel to a board. Each panel answers one question and reads at a glance: a number, a line or a bar. Build it from the structured types; `sql` is the last resort. Choose in this order: `funnel` for conversion through ordered events (viewed pricing → started checkout → paid), with a breakdown for conversion per segment (per shop, per plan): always a funnel, never a query or trend lines per step. `retention` for whether people come back. `trends` for everything that counts or sums events: `chart` "scalar" for one number (revenue, installs, failed charges; several numbers are several scalar panels, never one wide table), "line" for a metric over time, "bar" to compare segments over time, "hbar" to rank them, "share" for parts of a whole, "heatmap" for when in the week; set `display.format` to "currency" for money and "percent" for a rate. A rate is a number, never a table: the share of people who went on to do something is a two-step `funnel`, and a rate of events is a "scalar" that averages a property sent as 0 or 100 (add the property to the event when it is missing; "percent" writes the value as it is, so 0 or 1 would read 0.3% for 30%). A series can carry its own `breakdown`, so one panel shows signups by plan beside checkouts by country; reach for that before SQL. A table only when the rows themselves are the point (the operations or shops to look at), with at most four columns. `issues` for the top errors, `text` for a heading over a row of panels: a single "## Heading" line renders as a slim section title. `sql` only when none of those can show it. One value from SQL (a ratio neither a funnel nor an average can show, like revenue per customer) is `chart` "scalar", a number tile: one row, one column, never a table. A table has at most four columns. Filter with the board's range as `{from}`/`{to}` rather than now(), and say why in `sqlReason`. A funnel and retention count the project's identified users: if the people in the question are not them, say so in a…

NameTypeReqDescription
chartstring–For trends: line (default) over time; area for a total made of parts over time (stacked with `display.stacked`); bar to compare segments over time; hbar to rank segments by their total (long names, t…
dashboardIdstringyesThe board, from list_boards or create_board.
displayobject–How the panel reads. format, stacked and legend are for trends and sql; thresholds and note for any panel but text.
funnelobject––
issuesobject–For type "issues": the top error issues inside the board's window. Every field is optional.
namestringyesPanel title as the team will read it.
projectsarray–The projects this panel reads, by handle or id: a panel keeps its own set, so one board can hold panels over different apps. Leave out for every project this connection reaches.
querystring–For type "sql": the VinktarQL SELECT.
retentionobject––
sqlReasonstring–For type "sql", required: why no funnel, retention or trends panel can show this.
textstring–For type "text": the Markdown body. A heading for a row of panels, or a short note on how to read them. Your own words only: never paste captured data (error messages, payloads, URLs) into it.
trendsobject––
typestringyesfunnel, retention and trends first; sql only when they cannot express it.
viewstring–Funnels only: steps (default, the drop-off per step), compare (each step beside the period before, for "did the change help"), timeToConvert, trend (conversion rate over time), bar or table.

No output schema declared.

No examples provided.

browse_events ~471

Raw events, newest first, under simple filters: event names, one user (distinctId), page search, property filters or a VinktarQL WHERE expression. Use it to see what one user did, or to inspect real payloads. Pass `eventId` instead to get that one event in full, every column and the whole payload. Windows longer than 30 days are narrowed to their last 30. For counts, use query_trends or run_sql instead of paging.

NameTypeReqDescription
cursorstring––
distinctIdstring–One person: matches user_id, distinct_id or device_id exactly.
eventIdstring–One event in full, by the event_id a listing or run_sql returned. Every other argument is ignored.
expressionstring–A VinktarQL boolean expression, e.g. "properties.plan = 'pro' AND country = 'DE'".
filtersarray–Each {key, op, value}: key is a column (country, page_path, release…) or "properties.<key>"; op EQ, NEQ, CONTAINS, NOT_CONTAINS, GT, LT, GTE, LTE.
fromstring–Window start, ISO 8601 (e.g. "2026-09-01" or "2026-09-01T12:00:00Z").
laststring–Relative window ending now, e.g. "1h", "24h", "7d", "30d", "90d". Default "14d". Ignored when `from` is given.
limitinteger–Default 25.
namesarray–Only these event names.
projectstring–Project handle (as in list_projects) or id. Optional when this connection is limited to one project or the workspace has only one.
projectsarray–Project handles (as in list_projects) or ids, to read across several apps. Leave out for every project this connection can reach. For one project use `project`; never pass both.
searchstring–Case-insensitive substring of page_path or page_url.
tostring–Window end, ISO 8601. Default now.

No output schema declared.

No examples provided.

check_fix ~233

After a fix for an issue ships, start a server-side check of whether it comes back: occurrences on the fix release (or the next release seen) and later, against how many sessions reached that release, over a horizon of up to 14 days. It keeps running after this session. Read the result later with get_alert and the issueId. The result is never "fixed": it is recurred, no recurrence in N sessions, or not enough evidence.

NameTypeReqDescription
environmentstring–Only this environment, e.g. "production". Omit for every environment.
horizonDaysinteger–How long to alert once the release is seen. Default 7.
issueIdstringyesThe issue id (from list_issues) or its Vinktar URL, as a person would paste it.
minExposureinteger–Sessions (or events) the release must reach before a clean result counts. Default 100.
releasestring–The release that carries the fix, exactly as the SDK reports it. Omit to alert the next release first seen after now.

No output schema declared.

No examples provided.

create_alert ~943

Create an alert: a query (source events, errors or sql; measure count or unique_users; filters; an optional groupBy; a window in minutes), a condition (above or below a threshold, or changed by a percent against the window before, a week earlier or the trailing week) and who hears it (recipients among members, saved channels, the team by default). Each series is judged on its own and a series that fired stays quiet for one window. Examples: new issues = source errors, lifecycle first_seen, condition above, threshold 0. Users affected = source errors, measure unique_users, windowMinutes 60, above 100. Signups dropped = source events, event signup, condition changed, changeDirection down, changePercent 50, compare week. Orders stopped = source events, event order_placed, below 1. You cannot name a webhook, a URL or an outside address: a person adds those in Vinktar. Only create an alert when the user asked for one.

NameTypeReqDescription
changeDirectionstring–changed: up, down or either (default).
changePercentnumber–changed: how far it has to move, in percent. Default 50.
channelsarray–Where it posts: saved channel ids from get_alert, or a Slack channel of the connected Slack as "#name".
comparestring–changed: against the window before (default), the same window a week earlier, or the trailing week's average.
conditionstring–above (default) or below a threshold, or changed by a percent against an earlier window.
environmentstring–errors: only this environment, e.g. "production". Omit for all.
eventstring–events: the event name, from get_schema; omit for every event.
eventFiltersobject–events: {combinator: "AND", filters: [{property: {scope: "event"|"person", key}, op, values: [...]}]}, as a panel series carries them.
everyMinutesinteger–How often it is checked. Default 5, or 1 for a lifecycle alert.
floornumber–changed: a change where both sides are under this is not news, so a quiet series going from 1 to 4 stays quiet.
groupBystring–events, sql: a property to split by; each value is judged on its own (up to 20).
issueIdstring–errors: one issue only.
lifecyclestring–errors: read the issues first_seen or regressed since the last check instead of their volume; pair with condition above 0.
linksarray–Links shown with every message, e.g. the team's runbook page: a label and an http or https URL each. Replaces the list.
measurestring–count (default) or unique_users.
minLevelstring–errors: the least severe level that counts.
namestringyesWhat it alerts on, as a person would say it: "Signups dropping", "New issues in production".
notifyTeamboolean–Also tell the owners and admins. Default: on when no recipients or channels are given.
pendingForinteger–Consecutive checks in breach before it fires, so one bad minute is not news. Default 1.
projectstring–Project handle (as in list_projects) or id. Optional when this connection is limited to one project or the workspace has only one.
projectsarray–Project handles (as in list_projects) or ids, to read across several apps. Leave out for every project this connection can reach. For one project use `project`; never pass both.
recipientsarray–Workspace members to email, by address. Outside addresses are refused: a person adds those in Vinktar.
releasestring–errors: only issues last seen on this release; a trailing * matches a prefix, e.g. "web@2.*".
sourcestring–What is read: events (default), errors or sql.
sqlstring–sql: VinktarQL whose last column is the value; filter with {from} and {to}.
textContainsstring–errors: only issues whose title, type or culprit contains this.
thresholdnumber–above, below: the line.
windowMinutesinteger–The trailing window in minutes. Default 60.

No output schema declared.

No examples provided.

create_board ~499

Create an empty board in the workspace, to leave the user a view of what you found; fill it with add_panel, where each panel says which projects it reads. First decide what kind of board the request is, from the decision the user wants to make with it: "launch" when one feature or release just shipped: is it used, by whom, does it convert, did it break anything; "conversion" when a funnel someone cares about: where people drop and which segment converts; "growth" when the business at a glance: new people, active people, conversions and money over time; "engagement" when how much and how often people use the product, and whether they come back; "revenue" when money: how much, from whom, and the path to paying; "acquisition" when where people come from and which channels bring the ones who sign up; "reliability" when what is breaking and whether it hurts the flows that matter; "custom" when none of the above: a board shaped around one specific question. The result is a plan for that kind, filled in with the project's own signup, activation, conversion and revenue events: follow it, dropping what the user did not ask about. If the request fits none, ask the user what the board is for before building. Pass `expiresInDays` for a board built for one launch, so it deletes itself afterwards instead of staying forever. Only do this when the user asked for a board or agreed to one.

NameTypeReqDescription
descriptionstring–One sentence saying what the board is for, at most 100 characters. It is the line under the board's title; a person can edit it in Vinktar.
expiresInDaysinteger–Delete the board this many days from today. Leave it out for a board that stays. A person can change or clear the date in Vinktar.
kindstringyesWhat the board is for; decides the plan that comes back.
namestringyes–
projectstring–Project handle (as in list_projects) or id. Optional when this connection is limited to one project or the workspace has only one.
projectsarray–Project handles (as in list_projects) or ids, to read across several apps. Leave out for every project this connection can reach. For one project use `project`; never pass both.

No output schema declared.

No examples provided.

define_event ~384

Define an event in the project's tracking plan: what it means, its role, the properties it carries (type, unit, whether every send must include it, an example) and where the code sends it. Call it in the same step as adding or changing a track() call, before any data arrives; and for existing events once you have read the code that sends them. It takes effect at once, labelled as written by an agent, and the team can correct it in Vinktar. get_setup_status then reports defined events that never arrive and sends missing a required property. Conventions (get_install_guide with section "conventions" has them all): new event names and property keys are snake_case, object then past-tense action (signed_up, report_exported); a description is one sentence of at most 100 characters and a longer one is refused; an event already shipping under another spelling is defined as it is sent, never renamed unasked. Do not overwrite a description the team wrote unless the user asks. Setup call: never counted.

NameTypeReqDescription
code_locationstring–Where the code sends it, as a repo path and line: "src/checkout/pay.ts:88".
descriptionstring–What happened and when it fires: one sentence, at most 100 characters. Longer is refused.
eventstringyesThe name exactly as the code sends it. For an event you are adding: snake_case, object then past-tense action, like report_exported.
projectstring–Project handle (as in list_projects) or id. Optional when this connection is limited to one project or the workspace has only one.
propertiesarray––
rolestring–The business moment it stands for, if any: signup, activation, conversion, revenue. "none" clears it.

No output schema declared.

No examples provided.

delete_board ~70

Delete a board with its panels. Only when the user asked for it, or agreed when you proposed it; name the board before you do. A person can restore it in Vinktar from the boards page for 30 days.

NameTypeReqDescription
dashboardIdstringyesThe board, from list_boards.

No output schema declared.

No examples provided.

delete_panel ~77

Remove a panel from its board. Only when the user asked for it, or agreed when you proposed it; say which panel before you do. The panel id is in get_board. A person can restore it in Vinktar from the boards page for 30 days.

NameTypeReqDescription
panelIdstringyesThe panel, from get_board.

No output schema declared.

No examples provided.

get_alert ~193

Read alerts and what they said. Pass alertId for one alert: its query and condition, whether it is on or snoozed, what its last check read per series, who hears it and what it said recently. issueId gives that issue's latest fix check (awaiting_release, watching, recurred, no_recurrence, not_enough_evidence or stopped, with exposure and recurrences on the fix release). Neither lists every alert in the project, what fired in the last 24 hours, and the saved channels an alert can post to.

NameTypeReqDescription
alertIdstring––
issueIdstring–The issue id (from list_issues) or its Vinktar URL, as a person would paste it.
projectstring–Project handle (as in list_projects) or id. Optional when this connection is limited to one project or the workspace has only one.

No output schema declared.

No examples provided.

get_board ~180

Read a board: every panel computed over a window with the change against the previous period, as headline numbers. The quickest way to answer "how are we doing" in the terms the team already tracks. Each panel shows its id, for update_panel and delete_panel.

NameTypeReqDescription
dashboardIdstringyesFrom list_boards.
fromstring–Window start, ISO 8601 (e.g. "2026-09-01" or "2026-09-01T12:00:00Z").
laststring–Relative window ending now, e.g. "1h", "24h", "7d", "30d", "90d". Default "14d". Ignored when `from` is given.
tostring–Window end, ISO 8601. Default now.

No output schema declared.

No examples provided.

get_install_guide ~227

The step-by-step guide for setting Vinktar up in the app you are working in: which SDK fits the stack (with current versions), the recommended file layout and environment variables, defining the tracking plan as you add events, proving it with get_setup_status, and the handover telling the person where each variable goes. Call this first when asked to install, set up or audit Vinktar, and follow it. It ends with Vinktar's conventions (event and property naming, descriptions, how an event changes, releases and environments, identifying users and connecting the browser visit to the server); pass section "conventions" for those alone before adding or changing a track() call in an app that is already set up. It answers before sign-in too, and then starts with where the person signs in from each app. Setup call: never counted.

NameTypeReqDescription
sectionstring–"conventions" returns only the naming and tracking conventions; "alerts" only how alerts work and how to point one at an agent. Default: the whole guide, which includes both.

No output schema declared.

No examples provided.

get_issue ~234

Everything needed to debug one error issue: what it is, its status and history, how often and for whom it happens in the window (by release, environment, browser, URL, tag), the latest occurrence's stack trace (source-mapped when available, each in-app frame linking to its file in the repository once the project's repository URL is set), breadcrumbs and request, and the product events that user sent in the 30 minutes before it.

NameTypeReqDescription
fromstring–Window start, ISO 8601 (e.g. "2026-09-01" or "2026-09-01T12:00:00Z").
issueIdstringyesThe issue id (from list_issues) or its Vinktar URL, as a person would paste it.
laststring–Relative window ending now, e.g. "1h", "24h", "7d", "30d", "90d". Default "14d". Ignored when `from` is given.
tostring–Window end, ISO 8601. Default now.

No output schema declared.

No examples provided.

get_project_keys ~138

The keys installing Vinktar needs: the project's public write key (VINKTAR_KEY) with the ingest host, the Sentry-compatible DSN and the Bugsnag-compatible endpoints, and whether a source-map upload key (VINKTAR_CLI_KEY, a secret) exists, with where a person creates one. The secret is never returned: tell the person to add it as a CI secret. Needs a read and write connection. Setup call: never counted.

NameTypeReqDescription
projectstring–Project handle (as in list_projects) or id. Optional when this connection is limited to one project or the workspace has only one.

No output schema declared.

No examples provided.

get_schema ~325

What a project tracks (or several, with `projects`, each under its own heading): event names with their volume over the last 30 days, the payload properties each event carries, user trait keys, and the columns and functions VinktarQL (run_sql) accepts. Call before any query so names are real. Pass `event` to see every property of one event, or `propertyKey` to see that property's most common values, which is how you find the exact spelling of one before filtering on it.

NameTypeReqDescription
eventstring–Show only this event, with all of its property keys.
limitinteger–With `propertyKey`: how many values, default 30.
projectstring–Project handle (as in list_projects) or id. Optional when this connection is limited to one project or the workspace has only one.
projectsarray–Project handles (as in list_projects) or ids, to read across several apps. Leave out for every project this connection can reach. For one project use `project`; never pass both.
propertyKeystring–Instead of the schema: the most frequent values of this property over the last 90 days, most common first. E.g. "plan" (scope event), "country" (scope context), "company" (scope user).
propertyScopestring–Where `propertyKey` lives. Default "event" (a payload property).
searchstring–With `propertyKey`: a case-insensitive substring to narrow the values.

No output schema declared.

No examples provided.

get_setup_status ~122

Check a project's Vinktar install from the data that actually arrived: events and errors received, users identified, releases and environments tagged, source maps for the latest release, items the SDK dropped, and key events described. Each gap comes with the next step. Call it after installing, and again after each fix, until nothing is left to do. Setup call: never counted against the agent allowance.

NameTypeReqDescription
projectstring–Project handle (as in list_projects) or id. Optional when this connection is limited to one project or the workspace has only one.

No output schema declared.

No examples provided.

get_start_status ~77

Whether events and errors have arrived for a project started with start_project, by its write key, and whether the person has claimed it yet. Call it after installing the SDK and sending a first event. Projects someone already claimed answer only after sign-in, through get_setup_status.

NameTypeReqDescription
keystringyesThe write key start_project returned.

No output schema declared.

No examples provided.

list_boards ~120

The boards whose panels read from a project, or from any of several with `projects`. A board shows what the team already decided matters; read one with get_board.

NameTypeReqDescription
projectstring–Project handle (as in list_projects) or id. Optional when this connection is limited to one project or the workspace has only one.
projectsarray–Project handles (as in list_projects) or ids, to read across several apps. Leave out for every project this connection can reach. For one project use `project`; never pass both.

No output schema declared.

No examples provided.

list_issue_occurrences ~113

Recent individual occurrences of one issue, newest first: when, which user and session, release, environment, page, browser and OS. Use it to spot a pattern (one browser, one release, one customer) or to pick a user or session to follow in browse_events.

NameTypeReqDescription
cursorstring––
issueIdstringyesThe issue id (from list_issues) or its Vinktar URL, as a person would paste it.
limitinteger–Default 15.

No output schema declared.

No examples provided.

list_issues ~334

Error-tracking issues (errors grouped by fingerprint) for a project, or across several with `projects`, with occurrences and affected users inside the window. Default: open issues (unresolved + regressed) sorted by occurrences over the last 14 days. Follow up with get_issue for the stack trace.

NameTypeReqDescription
cursorstring––
environmentstring––
fromstring–Window start, ISO 8601 (e.g. "2026-09-01" or "2026-09-01T12:00:00Z").
laststring–Relative window ending now, e.g. "1h", "24h", "7d", "30d", "90d". Default "14d". Ignored when `from` is given.
levelarray––
limitinteger–Default 20.
projectstring–Project handle (as in list_projects) or id. Optional when this connection is limited to one project or the workspace has only one.
projectsarray–Project handles (as in list_projects) or ids, to read across several apps. Leave out for every project this connection can reach. For one project use `project`; never pass both.
releasestring––
searchstring–Matches title, error type or message.
sortstring–Default "occurrences"; "first_seen" surfaces new issues.
statusstring–Default "open".
tostring–Window end, ISO 8601. Default now.

No output schema declared.

No examples provided.

list_projects ~56

List the Vinktar projects this connection can read (a project is one app or site sending events and errors), with the workspace plan and what this connection is allowed to do. Call this first when you do not know the project handle.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

query_funnel ~435

Conversion through an ordered sequence of events (e.g. view_pricing → start_checkout → purchase): how many entered, how many reached each step, where they dropped, how long converting took, optionally by segment.

NameTypeReqDescription
breakdownobject–{scope, key}. scope "event" = payload property, "context" = built-in dimension (country, browser, page_path, utm_source…), "session", "user" = user trait.
conversionWindowobject–How long an entrant has to finish, e.g. {value: 1, unit: "day"}. Default 1 day.
filtersobject–Filters combined with AND/OR: {combinator: "AND", filters: [{property: {scope, key}, op, values: [..]}], groups: [nested groups]}. Ops: eq, neq, in, contains, gt, lt, is_set. Values are strings.
fromstring–Window start, ISO 8601 (e.g. "2026-09-01" or "2026-09-01T12:00:00Z").
laststring–Relative window ending now, e.g. "1h", "24h", "7d", "30d", "90d". Default "14d". Ignored when `from` is given.
orderstring–"ordered" (default): steps in sequence, other events allowed between; "strict": nothing between; "any": any order.
projectstring–Project handle (as in list_projects) or id. Optional when this connection is limited to one project or the workspace has only one.
projectsarray–Project handles (as in list_projects) or ids, to read across several apps. Leave out for every project this connection can reach. For one project use `project`; never pass both.
stepsarrayyesOrdered steps: {event, label?, filters?}.
tostring–Window end, ISO 8601. Default now.

No output schema declared.

No examples provided.

query_retention ~388

Cohort retention: users who did targetEvent in a period form a cohort, and the table shows what share of each cohort did returningEvent in each later period. Use it for "do people come back" and "did retention improve after the change".

NameTypeReqDescription
filtersobject–Filters combined with AND/OR: {combinator: "AND", filters: [{property: {scope, key}, op, values: [..]}], groups: [nested groups]}. Ops: eq, neq, in, contains, gt, lt, is_set. Values are strings.
fromstring–Window start, ISO 8601 (e.g. "2026-09-01" or "2026-09-01T12:00:00Z").
laststring–Relative window ending now, e.g. "1h", "24h", "7d", "30d", "90d". Default "14d". Ignored when `from` is given.
periodstring–Cohort granularity. Default "week".
periodsinteger–Periods each cohort is tracked for. Default 8.
projectstring–Project handle (as in list_projects) or id. Optional when this connection is limited to one project or the workspace has only one.
projectsarray–Project handles (as in list_projects) or ids, to read across several apps. Leave out for every project this connection can reach. For one project use `project`; never pass both.
returningEventstringyesThe event that counts as coming back (e.g. "session_start").
targetEventstringyesThe event that puts a user in a cohort (e.g. "signup").
tostring–Window end, ISO 8601. Default now.

No output schema declared.

No examples provided.

query_trends ~448

Metrics over time: event counts, unique users or sessions, the sum, average or p95 of a numeric property, optionally split by a property (one breakdown for every series, or each series by its own) and compared to the previous period. The workhorse for "how many / how much / is it growing" questions. interval "total" returns one de-duplicated number per series for the whole window.

NameTypeReqDescription
breakdownsarray–Split every series without its own `breakdown` by one property.
compareboolean–Also compute the previous period of equal length.
filtersobject–Filters combined with AND/OR: {combinator: "AND", filters: [{property: {scope, key}, op, values: [..]}], groups: [nested groups]}. Ops: eq, neq, in, contains, gt, lt, is_set. Values are strings.
fromstring–Window start, ISO 8601 (e.g. "2026-09-01" or "2026-09-01T12:00:00Z").
intervalstring–Bucket size. Default chosen from the window (hour ≤2d, day ≤120d, week beyond).
laststring–Relative window ending now, e.g. "1h", "24h", "7d", "30d", "90d". Default "14d". Ignored when `from` is given.
projectstring–Project handle (as in list_projects) or id. Optional when this connection is limited to one project or the workspace has only one.
projectsarray–Project handles (as in list_projects) or ids, to read across several apps. Leave out for every project this connection can reach. For one project use `project`; never pass both.
seriesarrayyesOne to five metrics. Each: {event, aggregation, property?, filters?, label?, breakdown?}. `property` is required for sum, avg and p95.
tostring–Window end, ISO 8601. Default now.

No output schema declared.

No examples provided.

run_sql ~308

Run a read-only VinktarQL SELECT over the project's `events` table, for anything query_trends, query_funnel and query_retention cannot express; start with those, since what they run is what a board panel should be. A ClickHouse-flavoured subset: WHERE, GROUP BY, HAVING, ORDER BY, LIMIT, DISTINCT, IN, LIKE and allowlisted functions (count, uniq, sum, avg, quantile, countIf, toStartOfDay…); no joins, subqueries, CTEs or INTERVAL, so filter time as `timestamp > now() - 86400 * 7`. Payload properties are `properties.<key>`, user traits `user.<key>`. Tenant scoping and plan retention are applied automatically. Call get_schema first for columns, functions and property names, and aggregate in SQL rather than paging through raw rows.

NameTypeReqDescription
cursorstring–The cursor from a previous page, to continue.
limitinteger–Rows per page, default 100.
projectstring–Project handle (as in list_projects) or id. Optional when this connection is limited to one project or the workspace has only one.
projectsarray–Project handles (as in list_projects) or ids, to read across several apps. Leave out for every project this connection can reach. For one project use `project`; never pass both.
querystringyesOne SELECT statement over `events`.

No output schema declared.

No examples provided.

set_project_notes ~152

Write the project's notes for AI agents: what the product does and for whom, the flows that matter (signup, activation, the paid action), what counts as an active user, and anything that makes the data easy to misread. Write them from the codebase during setup, in plain sentences, up to 2,000 characters; they replace the current notes, so read them in get_schema first and keep what the team wrote. Every later agent reads them before the data. Setup call: never counted.

NameTypeReqDescription
notesstringyes–
projectstring–Project handle (as in list_projects) or id. Optional when this connection is limited to one project or the workspace has only one.

No output schema declared.

No examples provided.

start_project ~188

Before the person has signed in to Vinktar: start a project for their app now, so setup can run and data can arrive before anyone makes an account. Returns the project's write key (public, safe in browser code) and a claim link that only the person should open: it signs them in, or makes them an account, and keeps the project with its data. Unclaimed, the project takes up to 10,000 events and is deleted with its data after 7 days. Only call it when the person has not signed in and the other tools ask for sign-in; once signed in, use list_projects and get_project_keys instead.

NameTypeReqDescription
namestringyesWhat the person calls the app, e.g. the repository or product name.
platformstring–The stack, e.g. "nextjs", "laravel", "node", "browser".

No output schema declared.

No examples provided.

update_alert ~758

Change an alert from get_alert: any part of its query, condition, timing, recipients (workspace members) and channels (saved ids or "#name" in the connected Slack). Or hold its news with snoozeMinutes (0 ends a snooze; a week at most). Switching an alert off or deleting it is a person's, in Vinktar. Only change an alert when the user asked.

NameTypeReqDescription
alertIdstringyes–
changeDirectionstring–changed: up, down or either (default).
changePercentnumber–changed: how far it has to move, in percent. Default 50.
channelsarray–Where it posts: saved channel ids from get_alert, or a Slack channel of the connected Slack as "#name".
comparestring–changed: against the window before (default), the same window a week earlier, or the trailing week's average.
conditionstring–above (default) or below a threshold, or changed by a percent against an earlier window.
environmentstring–errors: only this environment, e.g. "production". Omit for all.
eventstring–events: the event name, from get_schema; omit for every event.
eventFiltersobject–events: {combinator: "AND", filters: [{property: {scope: "event"|"person", key}, op, values: [...]}]}, as a panel series carries them.
everyMinutesinteger–How often it is checked. Default 5, or 1 for a lifecycle alert.
floornumber–changed: a change where both sides are under this is not news, so a quiet series going from 1 to 4 stays quiet.
groupBystring–events, sql: a property to split by; each value is judged on its own (up to 20).
issueIdstring–errors: one issue only.
lifecyclestring–errors: read the issues first_seen or regressed since the last check instead of their volume; pair with condition above 0.
linksarray–Links shown with every message, e.g. the team's runbook page: a label and an http or https URL each. Replaces the list.
measurestring–count (default) or unique_users.
minLevelstring–errors: the least severe level that counts.
namestring–What it alerts on, as a person would say it: "Signups dropping", "New issues in production".
notifyTeamboolean–Also tell the owners and admins. Default: on when no recipients or channels are given.
pendingForinteger–Consecutive checks in breach before it fires, so one bad minute is not news. Default 1.
recipientsarray–Workspace members to email, by address. Outside addresses are refused: a person adds those in Vinktar.
releasestring–errors: only issues last seen on this release; a trailing * matches a prefix, e.g. "web@2.*".
snoozeMinutesinteger––
sourcestring–What is read: events (default), errors or sql.
sqlstring–sql: VinktarQL whose last column is the value; filter with {from} and {to}.
textContainsstring–errors: only issues whose title, type or culprit contains this.
thresholdnumber–above, below: the line.
windowMinutesinteger–The trailing window in minutes. Default 60.

No output schema declared.

No examples provided.

update_board ~339

Rename a board, rewrite the line under its title, change when it deletes itself, or lay its panels out. A board is a grid: every row spans the full width, its panels share it (one to four) at one height, equally unless you give widths. Pass `rows` to set the layout outright, top to bottom, as rows of panel ids from get_board; panels you leave out keep their order after them. Or pass `arrange` to straighten the rows as they read now. Pass only what changes. Panels are changed with update_panel and delete_panel.

NameTypeReqDescription
arrangeboolean–Straighten the rows in their current order: numbers together, charts in pairs, one height per row.
dashboardIdstringyesThe board, from list_boards.
descriptionstring–One sentence saying what the board is for, at most 100 characters. Empty clears it.
expiresInDaysinteger–Delete the board this many days from today; 0 keeps it for good.
namestring––
rowsarray–The rows, top to bottom, e.g. [["12","13","14","15"],{"panels":["16","17"],"widths":[8,4]},["18"]]: numbers up to four to a row, charts two, a table or text on its own. A row is its panel ids, shared…

No output schema declared.

No examples provided.

update_issue ~242

Change an error issue's status or assignee: resolve it (optionally in the release that ships the fix, or in the next release when it has not shipped yet, so a later occurrence reopens it as a regression), ignore it, reopen it, or assign it to a teammate. Only act on an issue when the user asked you to.

NameTypeReqDescription
assigneestring–"me", a teammate's email, or "none" to unassign.
environmentstring–With status "ignored" or "unresolved": act in this environment only (ignore it in staging, keep it live in production).
issueIdstringyesThe issue id (from list_issues) or its Vinktar URL, as a person would paste it.
resolvedInNextReleaseboolean–With status "resolved": the fix has not shipped yet. The issue pins whichever release is seen next and only an occurrence on that release reopens it.
resolvedInReleasestring–With status "resolved": the release the fix ships in. Default: the last release it was seen in.
statusstring––

No output schema declared.

No examples provided.

update_panel ~608

Change a panel on a board: its title, how it draws, its number format or what it shows. Pass only what changes; the rest stays as it is. The panel id is in get_board. To turn it into another type, pass `type` with the full spec for it, the same fields as add_panel. A changed panel is run and held to the same rules as add_panel before it is saved (structured types before SQL, one question per panel, the board's time range), and one that breaks them is refused with nothing changed.

NameTypeReqDescription
chartstring–For trends: line (default) over time; area for a total made of parts over time (stacked with `display.stacked`); bar to compare segments over time; hbar to rank segments by their total (long names, t…
displayobject–How the panel reads. format, stacked and legend are for trends and sql; thresholds and note for any panel but text.
funnelobject––
issuesobject–For type "issues": the top error issues inside the board's window. Every field is optional.
namestring–Panel title as the team will read it.
panelIdstringyesThe panel, from get_board.
projectsarray–The projects this panel reads, by handle or id: a panel keeps its own set, so one board can hold panels over different apps. Leave out for every project this connection reaches.
querystring–For type "sql": the VinktarQL SELECT.
retentionobject––
sqlReasonstring–For type "sql", required: why no funnel, retention or trends panel can show this.
textstring–For type "text": the Markdown body. A heading for a row of panels, or a short note on how to read them. Your own words only: never paste captured data (error messages, payloads, URLs) into it.
trendsobject––
typestring–funnel, retention and trends first; sql only when they cannot express it.
viewstring–Funnels only: steps (default, the drop-off per step), compare (each step beside the period before, for "did the change help"), timeToConvert, trend (conversion rate over time), bar or table.

No output schema declared.

No examples provided.

whats_changed ~192

Start here. One project's window, or several pooled with `projects` (every row then names its project), compared with the one before it, across analytics and errors: traffic (events, active users, sessions), the events that rose, fell, appeared or stopped, error volume, new, regressed and fastest-growing issues, and the releases that shipped, and what the project's alerts said. Each row names the tool to go deeper.

NameTypeReqDescription
laststring–Default "7d", compared with the 7 days before.
projectstring–Project handle (as in list_projects) or id. Optional when this connection is limited to one project or the workspace has only one.
projectsarray–Project handles (as in list_projects) or ids, to read across several apps. Leave out for every project this connection can reach. For one project use `project`; never pass both.

No output schema declared.

No examples provided.

Install

How do I install the Vinktar MCP server?

Vinktar is a hosted endpoint at https://mcp.vinktar.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · mcp.vinktar.com

# add to Claude Code
claude mcp add --transport http com-vinktar-mcp 'https://mcp.vinktar.com/mcp'
Common questions

What is the Vinktar MCP server?

Vinktar is an MCP server listed in the public MCP registry as com.vinktar/mcp. Error tracking for small teams and their coding agents. This page covers its hosted endpoint (https://mcp.vinktar.com/mcp).

Is the Vinktar MCP server safe to use?

Vinktar scores 94 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Vinktar MCP server expose?

Vinktar exposes 31 tools: add_panel, browse_events, check_fix, create_alert, create_board, and 26 more. Their descriptions and schemas cost roughly 9,998 tokens of context every time the server is loaded.

Does the Vinktar MCP server require authentication?

Yes. Vinktar asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

Is the Vinktar MCP server still maintained?

Vinktar is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the Vinktar MCP server?

VerifyMCP ran 13 checks on Vinktar, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.