Nopaque TotalPath
REMOTE · MCP.NOPAQUE.CO.UK
Map, test and load-test IVRs and AI voice agents over real phone calls with TotalPath.
Available components
Last scanned (15 hours ago)
Scores higher than 51% of remote servers
Reachable. Last reached 21 Nov 2026.
Category Testing and QA
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 Security57
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation not fully verified: this server exposes a tool marked destructive (cancelMapping) and its handshake is open, but we could not confirm whether a tool call is gated, so we do not assert it is callable unauthenticated. View diagnostics → Unverified
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability65
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 24905 tokens (~262/item across 95 items; 95 tools + 0 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 Management29
- Stability check failed: schema churn in the 10 days we've observed: 0 tool removals, 5 breaking changes, 0 auth/transport breaks, 36 additions. See how to fix → Fail
Tool Coverage94
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 79% of tool parameters carry a description.Partial
- Structured output schemas are declared (99% of tools); any adoption earns full credit.Pass
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 96 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
Checks we ran (12)
- TLS certificate
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (1)
These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Authorization in Endpoint SecurityAuthorisation not fully verified: this server exposes a tool marked destructive (cancelMapping) and its handshake is open, but we could not confirm whether a tool call is gated, so we do not assert it is callable unauthenticated.
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 →
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.
- 20 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 22 to 26.
- 18 Nov 26 +1
- Tool “listMissionTests” rewrote its description, which is the text the model reads security
- “listMissionTests” reworded the description of “tags” cosmetic
- 17 Nov 26 0
- The server rewrote its instructions, which are the text every model session reads security
- New tool “runDigitalTest”, which the server declares destructive security
- New tool “runTest”, which the server declares destructive security
- New tool “startMapping”, which the server declares destructive security
- Tool “createMapping” rewrote its description, which is the text the model reads security
- Tool “getClaimLink” rewrote its description, which is the text the model reads security
- Tool “getMapping” rewrote its description, which is the text the model reads security
- Tool “listMappings” rewrote its description, which is the text the model reads security
- Tool “registerWorkspace” rewrote its description, which is the text the model reads security
- Tool “requestAnchorCode” rewrote its description, which is the text the model reads security
- Tool “verifyAnchorCode” rewrote its description, which is the text the model reads security
- Schema quality: 21765 → 24843 ▼ functional
- Tool coverage: 88% → 79% ▼ functional
- New tool “createDigitalConnector” functional
- New tool “createDigitalTestConfig” functional
- New tool “createMissionTestConfig” functional
- New tool “createProfile” functional
- New tool “createTestConfig” functional
- “createMapping” reworded the description of “profileId” cosmetic
- 15 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 6 to 9.
- 14 Nov 26 0
- Tool “listMissionTests” rewrote its description, which is the text the model reads security
- “listMissionTests” reworded the description of “tags” cosmetic
- 13 Nov 26 0
- Stability: 0.03 → fail ▼ security
- A breaking change shipped without a version bump: still 0.1.0 ▼ security
- The server rewrote its instructions, which are the text every model session reads security
- Tool “aggregateTestRuns” rewrote its description, which is the text the model reads security
- Tool “createMapping” rewrote its description, which is the text the model reads security
- Tool “getMapping” rewrote its description, which is the text the model reads security
- Tool “getMappingTree” rewrote its description, which is the text the model reads security
- Tool “getMissionTestConfig” rewrote its description, which is the text the model reads security
- Tool “getMissionTestRun” rewrote its description, which is the text the model reads security
- Tool “getWorkspaceUsage” rewrote its description, which is the text the model reads security
- Tool “listLoadTests” rewrote its description, which is the text the model reads security
- Tool “listMappings” rewrote its description, which is the text the model reads security
- Tool “listMissionTestConfigs” rewrote its description, which is the text the model reads security
- Tool “listTestRuns” rewrote its description, which is the text the model reads security
- Tool “createMapping” no longer declares itself destructive security
- “getUsageBySource” dropped the required parameter “workspaceId” ▼ functional
- “getWorkspacePlan” dropped the required parameter “workspaceId” ▼ functional
- “getWorkspaceUsage” dropped the required parameter “workspaceId” ▼ functional
- “getWorkspaceUsageThisPeriod” dropped the required parameter “workspaceId” ▼ functional
- “listWorkspaceInvoices” dropped the required parameter “workspaceId” ▼ functional
- Schema quality: 278 → 250 ▲ functional
- New tool “getBatch” functional
- New tool “getBatchRun” functional
- New tool “getCarrierIntegration” functional
- New tool “getDataset” functional
- New tool “getLoadTest” functional
- New tool “getLoadTestFailurePatterns” functional
- New tool “getLoadTestStatus” functional
- New tool “getMissionTest” functional
- New tool “getProfile” functional
- New tool “getReport” functional
- New tool “getSchedule” functional
- New tool “getSurveyResult” functional
- New tool “getSurveyTestConfig” functional
- New tool “listBatchRuns” functional
- New tool “listBatches” functional
- New tool “listCarrierIntegrations” functional
- New tool “listCarrierRoutes” functional
- New tool “listDatasets” functional
- New tool “listLoadTestRuns” functional
- New tool “listMappingPathRules” functional
- New tool “listMappingRuns” functional
- New tool “listMappingSteps” functional
- New tool “listMissionTests” functional
- New tool “listReports” functional
- New tool “listSchedules” functional
- New tool “listSurveyResults” functional
- New tool “listSurveyRuns” functional
- New tool “listSurveyTestConfigs” functional
- “getComplianceReportByPhone” reworded the description of “phoneNumber” cosmetic
- 12 Nov 26 +1
- Stability: unverified → 0.03 ▲ functional
- 11 Nov 26 62
First indexed and scored.
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.nopaque.co.uk
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=mcp.nopaque.co.uk | CN=Amazon RSA 2048 M04,O=Amazon,C=US | 14 Oct 2026 | 29 Apr 2027 | RSA 2048 | SHA256-RSA | 770ac81dc71fc034c026b1b4f3a93e0 |
| SANs: mcp.nopaque.co.uk | ||||||
| CN=Amazon RSA 2048 M04,O=Amazon,C=US (CA) | CN=Amazon Root CA 1,O=Amazon,C=US | 23 Aug 2022 | 23 Aug 2030 | RSA 2048 | SHA256-RSA | 773124f2a952e3ed18a58bdb85d1bc0ce5f27 |
| CN=Amazon Root CA 1,O=Amazon,C=US (CA) | CN=Starfield Services Root Certificate Authority - G2,O=Starfield Technologies\, Inc.,L=Scottsdale,ST=Arizona,C=US | 25 May 2015 | 31 Dec 2037 | RSA 2048 | SHA256-RSA | 67f944a2a27cdf3fac2ae2b01f908eeb9c4c6 |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of mcp.nopaque.co.uk. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| uk. | DS published | 43876 | 8 | Verified |
| co.uk. | DS published | 11810 | 8 | Verified |
| nopaque.co.uk. | No DS | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://mcp.nopaque.co.uk | Verified | 200 | |
| http (plaintext) | http://mcp.nopaque.co.uk | HTTPS enforced |
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 →
listTestRuns List Test Runs ~605
List test runs (mission/compliance/standard/param) with rich filters: runType, outcome (PASS/FAIL/ERROR/INCONCLUSIVE), phoneNumber, configId, catalogueTestId, configName / configPhoneNumber (standard and param runs only: case-insensitive substring of the test name or run id, substring of the number it dials), date range (startedAfter/startedBefore), sort (startedAt/completedAt asc/desc), and cursor pagination. Use cases: "last 3 mission failures", "runs against phone +44… this week", "compliance fails in the last 24h", "latest run of the standard test called X" (use configName). There are two kinds of saved test: standard tests (listTestConfigs) and mission tests (listMissionTestConfigs). configId matches the runs of one saved test of either kind. configName never matches a mission test: if it finds nothing, look the test up in listMissionTestConfigs and filter by configId before telling the user a test has no runs. Rows carry ids, not test names: use getTestConfig or getMissionTestConfig to name one. For counts and percentages use aggregateTestRuns instead, never by paging through this list. D-11: Load tests live in a separate table — use listLoadTestRuns for their run history (listLoadTests lists the saved load tests); runType=load returns 400 here.
| Name | Type | Req | Description |
|---|---|---|---|
| catalogueTestId | string | – | Filter by compliance catalogue test ID. |
| configId | string | – | Filter by saved config UUID. Matches runs of a mission-test config and runs of a standard or param test config. |
| configName | string | – | Only standard and param runs whose test name contains this text, or whose run ID does. Case-insensitive. Does not match mission or compliance runs. |
| configPhoneNumber | string | – | Only standard and param runs whose test dials a phone number containing this text. |
| cursor | string | – | Opaque base64 pagination cursor from `nextCursor` in a previous response. |
| jobId | string | – | Legacy back-compat filter — list runs for a specific test job. |
| limit | integer | – | Maximum runs to return per page (1-200, default 50). Use `cursor` for the next page. |
| outcome | string | – | Filter by outcome. |
| phoneNumber | string | – | E.164 phone number filter. |
| runType | string | – | Filter by run type. `load` is rejected (D-11). |
| sortBy | string | – | Timestamp field to sort by. Defaults to `startedAt`. |
| sortDir | string | – | Sort direction. Defaults to `desc` (newest first). |
| startedAfter | string | – | ISO8601 lower bound for startedAt (inclusive). |
| startedBefore | string | – | ISO8601 upper bound for startedAt (inclusive). |
| Name | Type | Req | Description |
|---|---|---|---|
| nextCursor | string | – | Opaque base64 cursor; present only when more pages are available. |
| runs | array | yes | – |
No examples provided.
listWorkspaceInvoices List Invoices ~151
The latest invoices, newest first, at most 12: period, status, total in cents with `display` as the amount to quote, currency, and whether it is the current draft. The current draft invoice has isDraft true; it is the only answer to "what will we be billed", and it is a draft that can still change. There is no forecast. Quote each total by its `display`; never add up or convert amounts. No PDF links. Use when: someone asks about invoices, spend or the next bill. Owner or billing admin only; other roles get 403. Only a person signed in to the nopaque web app can call this; an API key is refused.
Input schema present but exposes no named parameters.
| Name | Type | Req | Description |
|---|---|---|---|
| invoices | array | yes | – |
No examples provided.
registerWorkspace Register a Workspace and Get an API Key ~439
Create a new TotalPath workspace and receive an API key for it. No account, key or human is needed to call this. It is the first step for an agent that has no TotalPath credential yet. USE WHEN: - You have no TotalPath API key and want to start using this server - You have been asked to set up TotalPath from scratch DO NOT USE WHEN: - You already hold a TotalPath API key. Calling this again creates a second, separate, empty workspace. It does not add anything to the one you have. WHAT YOU GET BACK: - workspaceId: the new workspace's id - apiKey: your credential, beginning nq_. It is shown ONCE and cannot be retrieved again. Send it as the x-api-key header on every later call to this server (or Authorization: Bearer). Keep it out of transcripts and logs where you can. - keyPrefix: the first characters of the key, safe to show a person - scopes: what the key may do. It can create mappings and tests and read the balance. It can never buy capacity or change billing. WHAT THE WORKSPACE CAN DO AT THIS POINT: Create records only. It has NO calling capacity and cannot place a phone call until a human has verified a mobile number for it. Next, call requestAnchorCode. RATE LIMITS: A few registrations per hour from one network address. A refusal carries retryAfterSeconds. Do not retry in a loop. RELATED TOOLS: - requestAnchorCode, then verifyAnchorCode: get free calling capacity by verifying a human's mobile - getClaimLink: hand the workspace to a human so they can own it, add a card if a run is refused with VERIFICATION_REQUIRED, and pay for more capacity - getWorkspaceUsage: read the balance
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | A label for the workspace, up to 100 characters. Optional. Use the name of the product or team the calls are for, so the human who later claims the workspace recognises it. |
No output schema declared.
No examples provided.
requestAnchorCode Send a Verification Code to a Human's Mobile ~580
Send a one-time code by SMS to a human's mobile phone, to verify that a real person stands behind this workspace. This is what gives the workspace its free calling capacity. The code goes to the PHONE, not to you. You then need to ask that person what the code says and pass it to verifyAnchorCode. USE WHEN: - You have just called registerWorkspace and the workspace has no capacity yet - A person has agreed to be the accountable human for this workspace and has given you their mobile number THE HUMAN'S PART: Before calling this, tell the person that a text message is about to arrive and that you will need them to read the code back to you. Ask for the number in international format with the country code, for example +447700900123 or +12025550123. ARGUMENTS: - phoneNumber: the mobile number in E.164 format (a plus sign, country code, then digits, no spaces). Must be a MOBILE in the United Kingdom, Guernsey, Jersey, the Isle of Man or the United States. Landlines cannot receive the code. RESPONSE: - 202 with sent: true. The code is on its way. Now ask the person for it and call verifyAnchorCode with the same phoneNumber. WHEN IT IS REFUSED: - reason country_not_supported: only the countries above can be used - reason not_a_mobile: the number is a landline or similar - reason unparseable: check the format - reason anchor_limit_reached (403): this workspace already holds the maximum number of verified humans. Waiting will not help. One of them has to be replaced first, which a person does from workspace settings. Note this is not returned when you re-request a code for a number this workspace already holds: that resend is always allowed, and it is what to do if a verifyAnchorCode retry told you the code had expired. - reason already_anchored (409): that number is already the verified human for a different workspace. A number can stand behind one workspace at a time. - 429 with retryAfterSeconds: too ma…
| Name | Type | Req | Description |
|---|---|---|---|
| phoneNumber | string | yes | The mobile number to send the code to, in E.164 format, for example +447700900123. UK, Channel Islands, Isle of Man or US mobiles only. |
Structured output declared, but exposes no named fields.
No examples provided.
runComplianceTest Run Compliance Test ~452
Run a compliance test against a phone number. The test calls the number, executes a regulatory probe script (e.g., requests data deletion, asks about AI disclosure), and returns pass/fail per probe. Returns the run resource; poll getRunResults for completion.
| Name | Type | Req | Description |
|---|---|---|---|
| carrierRouteId | – | – | Bring-your-own-carrier (invite-only). Dial every test in this audit through one of the workspace's carrier routes, over the workspace's own SIP trunk, instead of nopaque's network. Carrier routes are… |
| phoneNumber | string | yes | Target phone number for the compliance probe, in E.164 format (e.g. `+442012345678`). All `testIds` in the batch are dispatched against this single number. |
| sector | string | yes | Regulatory sector to evaluate against (e.g. `financial-services`, `telco`, `all`). Each `testId` must declare this sector in its catalogue `sectors` array, or be tagged `sectors: [all]`. See `listCom… |
| testIds | array | yes | Array of compliance test IDs (one per probe) to run against `phoneNumber`. Each ID corresponds to one entry in `listComplianceCatalogue` (pattern `M-NNN`). Batch size is capped by the workspace tier'… |
| Name | Type | Req | Description |
|---|---|---|---|
| reportUrl | string | yes | Relative URL of the by-phone aggregator report. |
| runIds | array | yes | – |
No examples provided.
runDigitalTest Run a Chatbot Test ~142
Run a saved chatbot test now: nopaque holds the conversation with the chatbot and judges it against the acceptance. Takes the chatbot test `id` (from createDigitalTestConfig or listDigitalTestConfigs). Returns the run at once; read the outcome with getDigitalTestRun, which is usually ready after a minute or two. This uses the workspace's minutes or credit and cannot be undone; when a person is present, get a yes first. Use when: a chatbot test should be run.
| Name | Type | Req | Description |
|---|---|---|---|
| connectorId | string | – | Run against a different saved connector than the config's default. |
| id | string | yes | – |
| samples | integer | – | – |
Structured output declared, but exposes no named fields.
No examples provided.
runMissionTest Run Mission Test ~84
Launch a mission test run from an existing saved mission-test-config. A mission test calls a number, executes a scripted persona+goal+acceptance flow, and the LLM self-reports pass/fail against the acceptance criterion at end-of-call. Returns the run resource immediately; poll getMissionTestRun for verdict.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | Mission test config identifier. |
Structured output declared, but exposes no named fields.
No examples provided.
runTest Run a Scripted Test ~129
Run a saved scripted test now: nopaque calls the number and checks each step. Takes `testConfigId` (from createTestConfig or listTestConfigs). Returns the run at once; read the outcome with getRunResults, which is usually ready after a minute or two. This uses the workspace's minutes or credit and cannot be undone; when a person is present, get a yes first. Use when: a scripted test should be run, for example after a change to the phone system has been deployed.
| Name | Type | Req | Description |
|---|---|---|---|
| testConfigId | string | yes | The ID of the test configuration to execute. |
| Name | Type | Req | Description |
|---|---|---|---|
| callDurationSecs | number | – | Real call duration in seconds (post-answer → last node), surfaced from `callMetadata.callDurationSecs`. Preferred over the wall-clock diff (`completedAt − startedAt`), which inflates by 100–150s+ fro… |
| callTelemetry | object | – | Call-level telemetry captured during an IVR test call, nested onto `TestRun.callTelemetry`. Populated for standard, mission and compliance runs by the tester / mission-tester containers. nopaque's ow… |
| carrier | object | – | Bring-your-own-carrier (invite-only): the carrier route this run was dialled through, recorded when the run was dispatched. It still names that route after the config's `carrierRouteId` is changed or… |
| carrierDetail | object | – | Telnyx's record of this call, fetched once a few minutes after the call ends and stored on the run (absent until then). `status` is `not_found` when Telnyx had no record after three tries. Give `sipC… |
| carrierEvents | object | – | What the carrier's event log and the call recording say about this call, derived once a few minutes after the call ends and stored on the run (absent until then). Times named `...Secs` are seconds af… |
| completedAt | string | – | – |
| createdAt | string | – | – |
| failurePattern | object | – | Load-test calls that did not pass: why the call failed, as a named pattern with an owner and the values that put it there (`evidence`). Absent on passed calls, and on calls not yet classified. `rules… |
| id | string | yes | – |
| lateStart | boolean | – | Load-test calls: true when the system under test first spoke later after answer than the test's late-answer threshold (6 s by default), on passed and failed calls alike. Absent when nothing measured… |
| originalOutcome | string | – | Passed with note: the call's outcome before a `verdictNote` changed it to `PASS`. Absent unless a note changed the outcome. |
| outcome | string | – | Unified run outcome — see MissionTestRun.outcome. Optional/nullable for historical rows pre-backfill. |
| phoneNumber | string | – | – |
| startedAt | string | yes | – |
| status | string | yes | – |
| testConfigId | string | – | – |
| verdictNote | object | – | Passed with note: why a call (or step) that failed on its hold check counts as passed. `hold_unconfirmed`: the call reached hold and the line had sound on it, but the live check could not confirm mus… |
| workspaceId | string | yes | – |
No examples provided.
startMapping Start an IVR Map ~254
Start a run of a saved mapping job: nopaque calls the number, works through the menu and builds the tree. Takes the job `id` (from createMapping or listMappings). Returns the job with its current run; a run usually takes 2 to 15 minutes. Read progress with getMapping and the result with getMappingTree. This uses the workspace's minutes or credit and cannot be undone; when a person is present, get a yes first. Use when: straight after createMapping, or to run a saved map again.
| Name | Type | Req | Description |
|---|---|---|---|
| copyFromRun | integer | – | Run number to copy step data from for excluded paths (used when re-starting a job with `exclude` rules without re-mapping the excluded subtrees). |
| id | string | yes | Mapping-job identifier. |
| probeMode | boolean | – | Enable security-probe mode for this run. Requires a prior attestation via `POST /mapping/attest` for the target phone number; without one the call returns `403`. |
| toolConfig | object | – | Tool-config override for this run (analyzer + transcriber). |
| vertical | string | – | Vertical hint for prompt-library lookup (overrides job-level setting). |
| Name | Type | Req | Description |
|---|---|---|---|
| completedAt | string | – | Most-recent run completion timestamp. |
| config | object | yes | Per-job configuration knobs that govern exploration shape and call orchestration. Sensible defaults are applied server-side when fields are omitted on create. |
| createdAt | string | yes | Creation timestamp. |
| currentRun | object | – | Nested run summary on single-job responses (Phase 04 D-09 / D-10). `currentRun.status` is the run's own status (`queued`, `running`, `completed`, `failed` or `limited`); read it to decide whether the… |
| currentRunId | string | – | Identifier of the most-recent run (absent if never started). |
| error | string | – | Error message if the job failed. |
| id | string | yes | Unique mapping-job identifier. |
| inFlightCount | integer | – | Currently executing calls. |
| limitReason | string | – | Reason the run stopped early (only present when `status` is `limited`). |
| name | string | yes | Job display name. |
| phoneNumber | string | yes | Target phone number in E.164 format. |
| runNumber | integer | – | Flat-merged run number from the active or requested (via `?version=`) run. Phase 04 D-09 — preserved at top level for frontend back-compat alongside the new nested `currentRun` object. |
| startedAt | string | – | Most-recent run start timestamp. |
| stats | object | – | Aggregate statistics for the current run, populated while the job executes. |
| status | string | yes | On getMappingJob, the status of the run the response describes (a copy of `currentRun.status`, with `queued` shown as `idle`), or `idle` when the job has never run. createMappingJob returns `idle`: c… |
| tags | array | – | String labels for filtering and grouping. Lowercase alphanumeric + hyphens. |
| updatedAt | string | yes | Last update timestamp. |
| userId | string | yes | User who created the job. |
| workspaceId | string | yes | Owning workspace. |
No examples provided.
undoImport Undo a Sheet Import ~83
Delete the mission-test configs a committed import created, in the background. Takes `id`. A config changed since the import, or already deleted, is kept and listed in `undo.keptIds`. Returns at once with status undoing; poll getImport until undone. Use only when the user has asked to undo the import.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | Import identifier. |
Structured output declared, but exposes no named fields.
No examples provided.
verifyAnchorCode Verify the Code and Unlock Calling Capacity ~948
Submit the code the human read to you from their text message. On success the number is permanently recorded as this workspace's accountable human, and the workspace receives its free calling capacity for createMapping, runMissionTest and runComplianceTest. If a run is refused with errorCode VERIFICATION_REQUIRED, the workspace is on the Free plan and needs both a verified mobile and a card on file: call getClaimLink so the person can take the workspace over and complete the Verify page. If getClaimLink is refused with 409 workspace-claimed, the workspace already has an owner: that owner or an admin signs in to the TotalPath web app (the same environment as this server) and completes its Verify page (path /verify). The card is not charged on the Free plan. USE WHEN: - You called requestAnchorCode and the person has told you the code ARGUMENTS: - phoneNumber: the SAME number you passed to requestAnchorCode, in the same E.164 format - code: the digits from the text message, exactly as the person read them RESPONSE ON SUCCESS (200): - anchored: true. The human is verified. - freeGrantOutcome tells you about capacity: - granted: free capacity was added. Call getWorkspaceUsage to see how much. If your first run is refused with VERIFICATION_REQUIRED, call getClaimLink (see above). - already-granted: this workspace already had it. Nothing is wrong. - not-owed: this number has already used its one free allocation, on this or another workspace. The human is verified, but this verification adds no capacity. Call getWorkspaceUsage first: if the workspace still has capacity, carry on. If it has none, capacity has to be bought: call getClaimLink so the person can pay. If getClaimLink is refused with 409 workspace-claimed, the workspace already has an owner: that owner or an admin signs in to the TotalPath web app (the same environment as this server) and buys capacity under Settings, Billing (path /platform/settings/billing).…
| Name | Type | Req | Description |
|---|---|---|---|
| code | string | yes | The one-time code from the text message, as digits. |
| phoneNumber | string | yes | The same number the code was sent to, in E.164 format. |
| replaces | string | – | Optional, in E.164 format. Use ONLY when this person is taking over from someone whose number is already the verified human for this workspace — a colleague who has left, say. The new number is ancho… |
| Name | Type | Req | Description |
|---|---|---|---|
| anchored | boolean | yes | – |
| freeGrantError | string | – | Present only for `refused` (auth's reason, e.g. `not-an-agent-workspace`) and `unavailable` (the literal `unavailable`). |
| freeGrantOutcome | string | yes | `granted`: capacity added now. `already-granted`: the workspace already held it from an earlier call; nothing is wrong. `not-owed`: this number spent its one allocation before, on this workspace or a… |
| freeGrantOwed | boolean | yes | True when this anchor entitled the workspace to its free grant at the moment of anchoring, i.e. the grant was asked for on this call. False when the number had already spent its one allocation. |
| freeGranted | boolean | yes | Capacity was added to the workspace by THIS call. |
No examples provided.
How do I install the Nopaque TotalPath MCP server?
Nopaque TotalPath is a hosted endpoint at https://mcp.nopaque.co.uk/, 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.nopaque.co.uk
claude mcp add --transport http uk-co-nopaque-totalpath 'https://mcp.nopaque.co.uk/'
What is the Nopaque TotalPath MCP server?
Nopaque TotalPath is an MCP server listed in the public MCP registry as uk.co.nopaque/totalpath. Map, test and load-test IVRs and AI voice agents over real phone calls with TotalPath. This page covers its hosted endpoint (https://mcp.nopaque.co.uk).
Is the Nopaque TotalPath MCP server safe to use?
Nopaque TotalPath scores 66 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 Nopaque TotalPath MCP server expose?
Nopaque TotalPath exposes 95 tools: createMapping, getMapping, listMappings, cancelMapping, getMappingTree, and 90 more. Their descriptions and schemas cost roughly 24,561 tokens of context every time the server is loaded.
Does the Nopaque TotalPath MCP server require authentication?
No. We connected to Nopaque TotalPath without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Nopaque TotalPath MCP server still maintained?
Nopaque TotalPath 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 Nopaque TotalPath MCP server?
VerifyMCP ran 12 checks on Nopaque TotalPath, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about Nopaque TotalPath: Authorization. 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.