Voice quality analysis: PVQA and AQuA MOS for WAV files, VoIP call analysis for PCAPs
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Intrusive voice quality analysis (Sevana AQuA, wideband): compares a degraded/test WAV with its reference WAV and returns MOS, percent similarity and a fault analysis explaining the loss of quality. Upload both files first.
upload_id of the degraded/test WAV
upload_id of the original/reference WAV
test channel, from 0 (default: AQuA's choice)
reference channel, from 0 (default: AQuA's choice)
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http voice-quality https://mcp.sevana.biz/mcp
Intrusive voice quality analysis (Sevana AQuA, wideband): compares a degraded/test WAV with its reference WAV and returns MOS, percent similarity and a fault analysis explaining the loss of quality. Upload both files first.
| Argument | Type | Description |
|---|---|---|
| channel_test | null | integer | test channel, from 0 (default: AQuA's choice) |
| test_upload_id* | string | upload_id of the degraded/test WAV |
| channel_reference | null | integer | reference channel, from 0 (default: AQuA's choice) |
| reference_upload_id* | string | upload_id of the original/reference WAV |
{
"type": "object",
"required": [
"reference_upload_id",
"test_upload_id"
],
"properties": {
"channel_test": {
"type": [
"null",
"integer"
],
"description": "test channel, from 0 (default: AQuA's choice)"
},
"test_upload_id": {
"type": "string",
"description": "upload_id of the degraded/test WAV"
},
"channel_reference": {
"type": [
"null",
"integer"
],
"description": "reference channel, from 0 (default: AQuA's choice)"
},
"reference_upload_id": {
"type": "string",
"description": "upload_id of the original/reference WAV"
}
},
"additionalProperties": false
}Start uploading a WAV recording (kind "wav") or a packet capture (kind "pcap"). Returns an upload_id and a one-time upload_url; send the file as the body of an HTTP PUT to that URL (for example: curl -T recording.wav '<upload_url>'), then pass the upload_id to an analysis tool. The URL works once and expires after 15 minutes; the file is deleted after an hour. Use upload_inline instead if you can only pass tool arguments.
| Argument | Type | Description |
|---|---|---|
| kind | string | file kind: "wav" (default) or "pcap" (.pcap/.pcapng) |
| filename | string | original file name, for display only |
| size_bytes | integer | file size, if known; larger than the limit is refused at once |
{
"type": "object",
"properties": {
"kind": {
"type": "string",
"description": "file kind: \"wav\" (default) or \"pcap\" (.pcap/.pcapng)"
},
"filename": {
"type": "string",
"description": "original file name, for display only"
},
"size_bytes": {
"type": "integer",
"description": "file size, if known; larger than the limit is refused at once"
}
},
"additionalProperties": false
}Delete an uploaded file now instead of waiting for it to expire.
| Argument | Type | Description |
|---|---|---|
| upload_id* | string |
{
"type": "object",
"required": [
"upload_id"
],
"properties": {
"upload_id": {
"type": "string"
}
},
"additionalProperties": false
}Cancel a queued or running analysis job.
| Argument | Type | Description |
|---|---|---|
| job_id* | string |
{
"type": "object",
"required": [
"job_id"
],
"properties": {
"job_id": {
"type": "string"
}
},
"additionalProperties": false
}State of an analysis job (queued, running with stage and percent, done, failed, cancelled). Waits up to wait_seconds for it to finish; a finished PCAP job includes its summary.
| Argument | Type | Description |
|---|---|---|
| job_id* | string | |
| wait_seconds | null | integer | wait up to this many seconds for the job to finish (0-55, default 0) |
{
"type": "object",
"required": [
"job_id"
],
"properties": {
"job_id": {
"type": "string"
},
"wait_seconds": {
"type": [
"null",
"integer"
],
"description": "wait up to this many seconds for the job to finish (0-55, default 0)"
}
},
"additionalProperties": false
}Your analysis jobs from the last hour, newest first.
No arguments.
{
"type": "object",
"additionalProperties": false
}Start a VoIP quality analysis of an uploaded .pcap/.pcapng capture (upload it with kind "pcap"). Reconstructs SIP calls and RTP streams and scores every stream (Sevana MOS from the decoded speech, network MOS, loss, jitter). Returns a job_id; the call waits up to wait_seconds and, if the analysis finished by then, includes the summary. Otherwise poll job_status. Only analysis reports are returned, never decoded audio. Reports include SIP messages and DTMF digits as captured; they are kept for one hour.
| Argument | Type | Description |
|---|---|---|
| upload_id* | string | upload_id of a pcap upload |
| statistics | null | boolean | compute aggregate statistics across streams (default true) |
| wait_seconds | null | integer | wait up to this many seconds for the result (0-55, default 25) |
{
"type": "object",
"required": [
"upload_id"
],
"properties": {
"upload_id": {
"type": "string",
"description": "upload_id of a pcap upload"
},
"statistics": {
"type": [
"null",
"boolean"
],
"description": "compute aggregate statistics across streams (default true)"
},
"wait_seconds": {
"type": [
"null",
"integer"
],
"description": "wait up to this many seconds for the result (0-55, default 25)"
}
},
"additionalProperties": false
}DTMF key presses found in a finished PCAP analysis, with digits and timing: RTP telephone-events (RFC 2833/4733) per stream and SIP INFO (application/dtmf-relay, application/dtmf).
| Argument | Type | Description |
|---|---|---|
| job_id* | string | |
| call_id | string | only this call |
| stream_id | integer | only this RTP stream (RFC 2833 events) |
{
"type": "object",
"required": [
"job_id"
],
"properties": {
"job_id": {
"type": "string"
},
"call_id": {
"type": "string",
"description": "only this call"
},
"stream_id": {
"type": "integer",
"description": "only this RTP stream (RFC 2833 events)"
}
},
"additionalProperties": false
}The complete analysis report, one section at a time: "streams" or "sip_calls" (full objects, paged with cursor/limit) or "counters" (packet counters, SIP statistics, aggregate statistics). Contains no audio.
| Argument | Type | Description |
|---|---|---|
| limit | integer | items per page: streams default 5 (max 20), sip_calls default 3 (max 10); calls carry all their SIP messages |
| cursor | integer | index of the first item (from next_cursor) |
| job_id* | string | |
| section* | string | streams, sip_calls or counters |
{
"type": "object",
"required": [
"job_id",
"section"
],
"properties": {
"limit": {
"type": "integer",
"description": "items per page: streams default 5 (max 20), sip_calls default 3 (max 10); calls carry all their SIP messages"
},
"cursor": {
"type": "integer",
"description": "index of the first item (from next_cursor)"
},
"job_id": {
"type": "string"
},
"section": {
"type": "string",
"description": "streams, sip_calls or counters"
}
},
"additionalProperties": false
}One SIP call of a finished PCAP analysis: peers, user agents, response codes, timing, the SIP message ladder (method or status line per message), health warnings and the call's streams.
| Argument | Type | Description |
|---|---|---|
| job_id* | string | |
| call_id* | string | SIP Call-ID, as listed by pcap_summary |
{
"type": "object",
"required": [
"job_id",
"call_id"
],
"properties": {
"job_id": {
"type": "string"
},
"call_id": {
"type": "string",
"description": "SIP Call-ID, as listed by pcap_summary"
}
},
"additionalProperties": false
}Full detail of one RTP stream: quality (Sevana and network MOS, R-factor, impairments, echo), loss gaps, payload types, DTMF events. include_timeline adds PVQA's per-interval (0.68 s) detector table.
| Argument | Type | Description |
|---|---|---|
| job_id* | string | |
| stream_id* | integer | |
| include_timeline | boolean | add the per-interval PVQA detector table (large) |
{
"type": "object",
"required": [
"job_id",
"stream_id"
],
"properties": {
"job_id": {
"type": "string"
},
"stream_id": {
"type": "integer"
},
"include_timeline": {
"type": "boolean",
"description": "add the per-interval PVQA detector table (large)"
}
},
"additionalProperties": false
}Network view of a finished PCAP analysis: packet and SIP counters, per-stream loss, jitter, delay and network MOS, and the aggregate statistics (correlations of MOS with network features) when computed.
| Argument | Type | Description |
|---|---|---|
| job_id* | string |
{
"type": "object",
"required": [
"job_id"
],
"properties": {
"job_id": {
"type": "string"
}
},
"additionalProperties": false
}SIP messages of a finished PCAP analysis, exactly as captured (headers and SDP bodies), in time order. Filter by call_id; paged with cursor/limit.
| Argument | Type | Description |
|---|---|---|
| limit | integer | messages per page (default 50, max 200) |
| cursor | integer | index of the first message (from next_cursor) |
| job_id* | string | |
| call_id | string | only this call (default: all calls) |
{
"type": "object",
"required": [
"job_id"
],
"properties": {
"limit": {
"type": "integer",
"description": "messages per page (default 50, max 200)"
},
"cursor": {
"type": "integer",
"description": "index of the first message (from next_cursor)"
},
"job_id": {
"type": "string"
},
"call_id": {
"type": "string",
"description": "only this call (default: all calls)"
}
},
"additionalProperties": false
}Overview of a finished PCAP analysis: packet totals, SIP calls with their health warnings, and streams ordered worst Sevana MOS first, each with codec, MOS, loss, jitter and impairments.
| Argument | Type | Description |
|---|---|---|
| job_id* | string | |
| max_calls | integer | calls to list (default 50, max 200) |
| max_streams | integer | streams to list (default 50, max 200) |
{
"type": "object",
"required": [
"job_id"
],
"properties": {
"job_id": {
"type": "string"
},
"max_calls": {
"type": "integer",
"description": "calls to list (default 50, max 200)"
},
"max_streams": {
"type": "integer",
"description": "streams to list (default 50, max 200)"
}
},
"additionalProperties": false
}Non-intrusive voice quality analysis (Sevana PVQA) of an uploaded WAV file: predicted MOS (1-5) and the impairments found (low SNR, noise, dead air, clipping, clicks, echo, packet-loss artifacts, ...). No reference recording is needed. report_type "extended" adds the per-interval detector table.
| Argument | Type | Description |
|---|---|---|
| channel | integer | channel to analyze, from 0 (default 0); -1 mixes all channels |
| upload_id* | string | upload_id of a WAV file |
| report_type | string | "basic" (default) or "extended" (adds the per-interval table) |
{
"type": "object",
"required": [
"upload_id"
],
"properties": {
"channel": {
"type": "integer",
"description": "channel to analyze, from 0 (default 0); -1 mixes all channels"
},
"upload_id": {
"type": "string",
"description": "upload_id of a WAV file"
},
"report_type": {
"type": "string",
"description": "\"basic\" (default) or \"extended\" (adds the per-interval table)"
}
},
"additionalProperties": false
}Raw values of one PVQA detector over time for an uploaded WAV file. Detectors: SNR, DeadAir-00, DeadAir-01, Click, VADClip, AmpClip, DynClip, Echo, Noise, Crushed, DTMF.
| Argument | Type | Description |
|---|---|---|
| channel | integer | channel to analyze, from 0 (default 0) |
| detector* | string | detector name: SNR, DeadAir-00, DeadAir-01, Click, VADClip, AmpClip, DynClip, Echo, Noise, Crushed or DTMF |
| upload_id* | string | upload_id of a WAV file |
{
"type": "object",
"required": [
"upload_id",
"detector"
],
"properties": {
"channel": {
"type": "integer",
"description": "channel to analyze, from 0 (default 0)"
},
"detector": {
"type": "string",
"description": "detector name: SNR, DeadAir-00, DeadAir-01, Click, VADClip, AmpClip, DynClip, Echo, Noise, Crushed or DTMF"
},
"upload_id": {
"type": "string",
"description": "upload_id of a WAV file"
}
},
"additionalProperties": false
}Impairment timeline of an uploaded WAV file: which impairments PVQA detects at which time.
| Argument | Type | Description |
|---|---|---|
| channel | integer | channel to analyze, from 0 (default 0) |
| upload_id* | string | upload_id of a WAV file |
| resolution_ms | integer | time step of the returned rows in ms (default 250, min 10); each row holds the maximum of every numeric column in its window. Coarsened automatically to stay within 1000 rows |
{
"type": "object",
"required": [
"upload_id"
],
"properties": {
"channel": {
"type": "integer",
"description": "channel to analyze, from 0 (default 0)"
},
"upload_id": {
"type": "string",
"description": "upload_id of a WAV file"
},
"resolution_ms": {
"type": "integer",
"description": "time step of the returned rows in ms (default 250, min 10); each row holds the maximum of every numeric column in its window. Coarsened automatically to stay within 1000 rows"
}
},
"additionalProperties": false
}Analyzer versions, your tier (free or API key), your limits and how many analyses you have left.
No arguments.
{
"type": "object",
"additionalProperties": false
}Upload a WAV or pcap file as base64 in the tool arguments (2 MB at most after decoding). Returns an upload_id for the analysis tools. Larger files: use create_upload.
| Argument | Type | Description |
|---|---|---|
| kind | string | file kind: "wav" (default) or "pcap" |
| filename | string | original file name, for display only |
| content_base64* | string | the whole file, base64 encoded |
{
"type": "object",
"required": [
"content_base64"
],
"properties": {
"kind": {
"type": "string",
"description": "file kind: \"wav\" (default) or \"pcap\""
},
"filename": {
"type": "string",
"description": "original file name, for display only"
},
"content_base64": {
"type": "string",
"description": "the whole file, base64 encoded"
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 17, 2026.