MCP servers › io.github.sblattj › whosaid

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

io.github.sblattj/whosaid

Local speaker-attributed transcription and meeting search for Apple Silicon. Audio stays on the Mac. — the publisher's description

6 of 7 record checks metRead-only · tools listed 2026-10-23Topic: media-and-design · AI-classifiedversion 1.15.0PythonMITstandard input/output17 tools

Summary

io.github.sblattj/whosaid is a local MCP server listed in the official MCP registry at version 1.15.0. On 2026-10-23 ProtocolProbe started its published package in an isolated sandbox in read-only mode and read its inventory: 17 tools, 4 resources and 0 prompts.

Record checks

6 of 7 record checks met · 1 does not apply · 1 not checked

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met: The version the registry lists can be installed and is not withdrawn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

#11,684 of 15,112 packages by monthly downloads, tied with 36 others
Not ranked by stars: 5 stars (ranked from 10)

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

Key facts

Runs: local package
Transport: standard input/output
Package: PyPI · listed version current
License: MIT
Repository: public
Tools: 17
Described as changing data: 5 of 17 toolsAI-classified
Mainly works on: files and code on the machine it runs onAI-classified
Topic: media-and-designAI-classified
Last tested: 2026-10-23

Add to your client

Worth knowing before you connect it

5 tools are described as changing something (whosaid_transcribe, whosaid_relabel, whosaid_enroll_from_file, …): our AI model's reading of the descriptions, not something we tested. We did not call them.

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

How fresh this is

Live-tested

yes, a real session (not a text-only review)

Last tested

2026-10-23

Mode

read-only (no tool calls)

Latest version

1.15.0, published 2026-10-22 (registry, as of the 2026-10-23 snapshot)

First listed version

2026-10-20 (earliest version still in the registry; older removed versions would be earlier)

Version history

2 versions listed, 2026-10-20 to 2026-10-22; 2 in the 90 days before the 2026-10-23 snapshot.

Most recent 2 versions

1.15.0 · 2026-10-22
1.14.0 · 2026-10-20

(versions still listed in the registry only)

Registry data

snapshot 2026-10-23

Package and repository

checked 2026-10-23

Engine

mcp-runtime-engine@0.1.0 · sdk@1.32.0

Changes since the last refresh

New in the registry: not in the list of 2026-10-04, listed on 2026-10-23 with version 1.15.0 (published 2026-10-22).

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

What it is

What does this server offer?

Observed inventory

17tools

4resources

0prompts

What it mainly works on, as our AI model read its tool descriptions: files and code on the machine it runs on.

5 of 17 tools are described as changing something (creating, editing, deleting, sending or running).

whosaid_transcriberuns code or commandsdescribed as changing data
“Transcribe an audio file and label each turn with WHO said it — 100% locally on the Apple-Silicon GPU (no cloud, no API keys).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
12 inputs, 1 required
- audiostringrequired
- outdirstring or null
- accuracystring
- formatstring
- langstring
- speakersinteger or null
- min_speakersinteger or null
- max_speakersinteger or null
- expected_speakersarray or null
- anchor_thresholdnumber or null
- diarizeboolean
- match_thresholdnumber or null
whosaid_relabelcreates or changes datadescribed as changing data
“Put real names on SPEAKER_NN clusters and REMEMBER them: each name is saved to your local speaker registry and auto-applied to EVERY future transcript.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
12 inputs, 2 required
- basestringrequired
- assignmentsobjectrequired
- outdirstring or null
- autoboolean
- match_thresholdnumber or null
- rolesobject or null
- no_saveboolean
- forceboolean
- notestring or null
- fold_unknownboolean
- blendboolean
- forgetarray or null
whosaid_list_speakersreads or searches
“List the voices whosaid can already auto-name: enrolled clips in `voices/` plus voiceprints saved in the local speaker registry (~/.config/whosaid/speakers.json).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
whosaid_doctorreads or searches
“Read-only readiness check: Apple-Silicon/arch + macOS, ffmpeg and uv, Whisper and diarization model-cache state, enrolled voices, and the mic/audio device list.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
whosaid_enroll_from_filecreates or changes datadescribed as changing data
“Enroll a named voice from an EXISTING audio clip (≥15 s of one person speaking, reasonably clean) so future transcripts auto-label them — converts and writes voices/<Name>.wav.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
5 inputs, 2 required
- namestringrequired
- audiostringrequired
- ssstring or null
- tstring or null
- tostring or null
whosaid_samplescreates or changes datadescribed as changing data
“Export ONE short representative WAV clip per SPEAKER_NN cluster, cut from the ORIGINAL recording, so a human can quickly LISTEN and confirm an identity before trusting an auto-label or enrolling that…”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
4 inputs, 1 required
- basestringrequired
- outdirstring or null
- per_speakerinteger
- secondsnumber
whosaid_searchreads or searches
“Search every speaker-labeled transcript in a meeting workspace and get back the matching TURNS (meeting folder, timestamp, speaker, text, score), not whole files.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs, 1 required
- querystringrequired
- modestring
- speakerstring or null
- meetingstring or null
- kinteger
- workspacestring or null
whosaid_contextreads or searches
“Read the verbatim transcript turns around ONE moment of ONE meeting: `meeting` is the workspace folder name from a search hit, `at` its timestamp (HH:MM:SS or MM:SS), `before`/`after` the window in s…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs, 2 required
- meetingstringrequired
- atstringrequired
- beforeinteger
- afterinteger
- workspacestring or null
whosaid_itemsreads or searches
“List action items from the workspace's entity graph, filtered by `owner`, `requester`, `status` or `type`.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs
- ownerstring or null
- requesterstring or null
- statusstring or null
- typestring or null
- workspacestring or null
whosaid_itemreads or searches
“One action item by id (AI-NNN) with its full history: every meeting it came up in, the timestamped turns where it was discussed, commitments and status changes, related PRs.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
- idstringrequired
- workspacestring or null
whosaid_personreads or searches
“Per-person commitments view (GitHub issue #13): what `name` owns, what they asked others for, deadlines they gave, and the meetings they were in.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
- namestring or null
- workspacestring or null
whosaid_meetingsreads or searches
“List the meetings in the workspace as the graph knows them: folder, date, duration, attendees (speaker labels), action-item count, and kind (source origin: "teams-chat" for a Microsoft Teams chat fol…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
8 inputs
- workspacestring or null
- kindstring or null
- sincestring or null
- untilstring or null
- querystring or null
- limitinteger or null
- offsetinteger
- compactboolean

Show 5 more tools

whosaid_prsreads or searches
“List pull-request mentions found in the transcripts: PR numbers or links, who mentioned them, in which meeting and when.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
- workspacestring or null
- limitinteger or null
- offsetinteger
whosaid_speakersreads or searches
“List every speaker label in the search index with turn counts and the meetings they appear in.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
- workspacestring or null
- limitinteger or null
- offsetinteger
whosaid_workspace_statusreads or searches
“Read-only health check for a meeting workspace: whether the search index (_search.db) exists and what it holds (meetings, turns, embeddings), whether the rendered _WIKI.md, _ACTION-ITEMS.md and _INDE…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- workspacestring or null
whosaid_worklistreads or searches
“Ranked personal worklist (GitHub issue #13): what `owner` signed up for across every meeting, from the roll-up corpora (dev-commitments CM-NNN plus the action items AI-NNN they own), each item tiered…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs
- ownerstring
- tierstring or null
- limitinteger or null
- offsetinteger
- compactboolean
- workspacestring or null
whosaid_reprocessruns code or commandsdescribed as changing data
“Re-diarize meetings in a workspace whose speaker sidecars predate the v1.10 diarizer fixes (wraps `whosaid reprocess`).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
12 inputs
- workspacestring or null
- meetingsarray or null
- dry_runboolean
- all_meetingsboolean
- no_itemsboolean
- speakersinteger or null
- min_speakersinteger or null
- max_speakersinteger or null
- expected_speakersarray or null
- match_thresholdnumber or null
- enginestring or null
- hookstring or null

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

How well are its tools described?

Features #4 and #5

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

Descriptions

AI reading of each description

Says what the tool does: 100% of 17 tools
Says what it returns: 88% of 16 tools
States limits, defaults or errors: 38% of 16 tools
Says when to use it: 100% of 6 tools
Items covered per tool: 3.2 of 4 on average

Counted from the listing

Parameters with a description: 0% of 86
Tools with a description: 100% of 17
Typical description length: 662 characters

The tool set

Counted from the listing

Tools: 17
Size of the list: about 5,560 tokens for an agent to load (characters ÷ 4)
Naming: 17 of 17 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 17 of 17 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.

How do I add it to my client?

Config from the registry entry

No config: the PyPI package declares runtime arguments (options for the runner itself), and the registry documentation gives no rule for where they go.

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

Can it be installed, and is it up to date?

Version pin · advisories

Listed version

Registry lists: 1.15.0
Latest stable: 1.15.0
Status: current
Withdrawn: no

Source: pypi.org · 2026-10-23. About the version the registry lists; a manual install may resolve to a different one.

Integrity, provenance, license

Integrity: sha256-b7c1d94ae49f05eeb…
License: MIT

Source: the package registry · 2026-10-23.

Usage

Downloads: 152 in the last month

Source: pypistats.org · 2026-10-23.

Does the registry listing match what we found?

Feature #6

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

Registry says	We found	Result	Source · date
Published package can be started	Started and answered	matches	our test · 2026-10-23
Version 1.15.0 on PyPI	Exists and can be installed	matches	PyPI · 2026-10-23
Repository github.com/sblattj/whosaid	Opens publicly	matches	api.github.com · 2026-10-23

Who made it?

Feature #7 · lineage

Facts about the publisher. We do not turn them into a trust score.

Namespace: io.github.sblattj · 2 servers
GitHub owner: a personal account (sblattj)

Repository: github.com/sblattj/whosaid
Stars: 5
Repository age: 91–180 days
Last push: 0–30 days ago
Archived: no
Security policy: none found (we looked for SECURITY.md in the repository and in its owner’s .github repository)

Source: the registry entry and api.github.com · 2026-10-23; security policy read from GitHub · 2026-10-23.

Publish this server? Run these checks against it yourself before release, from your own machine: a server the command starts, or your own server at its URL after a one-time proof that you control it: npx protocolprobe-selftest.

Choosing

Record checks

Public records · not a safety rating

6 of 7 record checks met · 1 does not apply · 1 not checked

#11,684 of 15,112 packages by monthly downloads, tied with 36 others
Not ranked by stars: 5 stars (ranked from 10)

MetRegistry entry is active and says how to run itActive, with a package or a remote address.
MetSource repository link opensThe linked GitHub repository is public.
MetRepository is not archivedNot archived.
MetCode pushed to the repository in the 90 days before our checkLast push 0-30 days before our check.
Not metRepository publishes a security policy (SECURITY.md)No SECURITY.md in the places GitHub reads it from.
MetPackage names its licence with a standard (SPDX) identifierMIT
MetThe version the registry lists can be installed and is not withdrawnThe listed version exists and is current.
Does not applynpm package carries build provenance (attestation)PyPI packages have no npm-style attestation.
Not checkedNo known critical or high advisory in the package or its dependenciesWe could not resolve its dependencies.

Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-23. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating. How each check works · Leaderboards

Common questions about io.github.sblattj/whosaid

Answered from the data above

Is io.github.sblattj/whosaid safe to install?

We do not rate servers as safe or unsafe. 6 of its 7 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its source repository opens publicly. Its repository had a push in the last 90 days. The listed version is the latest stable release. The package itself has no known vulnerability (OSV.dev). 5 of its tools describe changing data (our AI model's reading of the descriptions). These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.

Has io.github.sblattj/whosaid been security tested?

Partly. 3 of the 12 checks that apply to it were exercised. We started the package in an isolated sandbox and read what it declares, but this test round was read-only, so its tools were not called. No security verdict is published before verification.

What can io.github.sblattj/whosaid do?

It lists 17 tools. In our AI model's reading of their descriptions (two runs had to agree, nobody checked it by hand), they include tools that read or search, create or change data and run code or commands. We did not call any tool, so this describes the text, not the behaviour.

Can io.github.sblattj/whosaid change or delete data?

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

Does io.github.sblattj/whosaid publish a security policy?

We found no SECURITY.md in its repository (root, .github/ or docs/) or in its owner's .github repository.

Is the listed version current?

Yes. The registry lists 1.15.0, the latest stable release on PyPI.

Where is the source code of io.github.sblattj/whosaid?

In github.com/sblattj/whosaid, which opens publicly.

Found this page useful?

Anonymous · no sign-in

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

Similar servers

Same topic · AI-read

io.github.tldraw/tldrawalso has tools that creates or changes data, runs code or commands, reads or searchescompare with this one
io.github.leancoderkavy/premiere-proMCP for Adobe Premiere Proalso has tools that creates or changes data, runs code or commands, reads or searchescompare with this one
io.github.kvoltmer/audionautAudionautalso has tools that creates or changes data, runs code or commands, reads or searchescompare with this one
io.github.KyaniteLabs/kinocutKinocutalso has tools that creates or changes data, runs code or commands, reads or searchescompare with this one
io.github.KyaniteLabs/mcp-videomcp-videoalso has tools that creates or changes data, runs code or commands, reads or searchescompare with this one
tech.kyanitelabs/kinocutKinocutalso has tools that creates or changes data, runs code or commands, reads or searchescompare with this one

Active servers whose topic is also “media-and-design” and that have at least one tool of the same kind; most kinds in common first, then most GitHub stars. The topic and the tool kinds are an AI model's reading of the publishers' descriptions, not checked by hand. Similar is not a recommendation.

Compare with another server

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

Security testing

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

18 checks · features #1, #2

Not probed (read-only run)

We started the package in an isolated sandbox and read what it declares, but this test round was read-only, so its tools were not called. No security score is given; a check we did not run is never counted as passed.

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

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

3 exercised9 not run (reason given)6 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 3 of the 12 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.

Exercised · 3

1Inventory
tool-listReads the declared tools, resources and prompts.exercised
2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised
12Hidden content
audience-hidingChecks resources that hide content from the user.exercised

Not run, with the reason · 9

3Real execution
real-executionCalls a tool and checks what really happens.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against

Does not apply to this server · 6

13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable
14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
17Consent handling
confused-deputyChecks consent handling when one service acts for another.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable

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

What happened during the test?

Feature #8

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

0 msStarted the published package in an isolated sandbox (read-only mode)
33,182 msConnected after 0 redirects.
Read the inventory: 17 tools, 4 resources, 0 prompts.
33,708 msFinished: 3 checks exercised.

Reference

How is it classified?

18 fields

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

TopicAI-classified

media-and-design

AI-classified · 2026-10-23

Pricing modelAI-classified

not checked

no website in the registry entry

Programming language

Python

api.github.com · 2026-10-23

Hosting type

local package

registry · 2026-10-23

MCP capability

prompts, resources, tools

our test · 2026-10-23

Transport

standard input/output

registry · 2026-10-23

Required credentials

none declared

registry · no declaration is not a guarantee

Package registry

pypi

registry · 2026-10-23

Freshness

0–30 days

registry updatedAt · 2026-10-23

Lifecycle status

active

registry · 2026-10-23

License class

permissive

package registry · 2026-10-23

Integrity hash

declared (sha256)

package registry · 2026-10-23

Signature / provenance

does not apply

PyPI publishes no registry signature or attestation equivalent to npm dist.signatures

Dependency advisories

not known (our limit)

uv could not resolve the dependency tree - our limitation

Popularity

152 downloads a month

package registry · 2026-10-23

Publisher signals

owner: a personal account · repository age: 91–180 days · stars: 0–9

api.github.com · 2026-10-23

Maintenance

active

api.github.com · 2026-10-23

Environment

your machine

where it runs, from the hosting type

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

Cite or correct this page

Sources and corrections

Suggested citation

ProtocolProbe. “io.github.sblattj/whosaid: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/io.github.sblattj/whosaid

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

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

Badge for your README

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/io.github.sblattj/whosaid)](https://protocolprobe.com/mcp/servers/io.github.sblattj/whosaid)

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

Something wrong, or is this yours?

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

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