MCP servers › io.github.photofresco › photofresco

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

io.github.photofresco/photofresco

Let AI agents edit images in a PhotoFresco window you approve: layers, masks, previews and export. — the publisher's description

4 of 5 record checks metRead-only · tools listed 2026-10-23Topic: media-and-design · AI-classifiedPricing: freemium · AI-classifiedversion 0.1.0JavaScriptstandard input/output38 tools

Summary

io.github.photofresco/photofresco is a local MCP server listed in the official MCP registry at version 0.1.0. On 2026-10-23 ProtocolProbe started its published package in an isolated sandbox in read-only mode and read its inventory: 38 tools, 0 resources and 0 prompts.

Record checks

4 of 5 record checks met · 4 do not apply

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)
not applicable: Package names its licence with a standard (SPDX) identifier
not applicable: The version the registry lists can be installed and is not withdrawn
not applicable: npm package carries build provenance (attestation)
not applicable: No known critical or high advisory in the package or its dependencies

Not ranked by downloads: not an npm or PyPI package
Not ranked by stars: 0 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: MCP bundle
Repository: public
Tools: 38
Described as changing data: 28 of 38 toolsAI-classified
Mainly works on: a web browser or desktop applicationsAI-classified
Topic: media-and-designAI-classified
Pricing: freemiumAI-classified
Last tested: 2026-10-23

Add to your client

Worth knowing before you connect it

28 tools are described as changing something (photofresco_connect, photofresco_request_access, photofresco_attach, …): 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: 0.1.0, published 2026-10-10 (registry, as of the 2026-10-23 snapshot)
First listed version: 2026-10-10 (earliest version still in the registry; older removed versions would be earlier)
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 0.1.0 (published 2026-10-10).

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

38tools

0resources

0prompts

What it mainly works on, as our AI model read its tool descriptions: a web browser or desktop applications.

28 of 38 tools are described as changing something (creating, editing, deleting, sending or running).

photofresco_connectcontrols a browser or desktopdescribed as changing data
“Open PhotoFresco in its own browser window on this computer and ask the user to allow this agent.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world yes
3 inputs
- accessobject“Permissions to ask the user for once connected.”
- documentstring“"active" (default), "none", or a document_id from photofresco_documents”
- wait_secondsnumber“Seconds to wait for the user's decision before returning the pending code (default 40)”
photofresco_statusreads or searches
“Connection state, the pending connection code, the session (target document_id, revision, granted permissions, pending permission request, credit budget, pause state), folders granted for import/expo…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
photofresco_request_accessdescribed as changing data
“Ask the user for permissions in the PhotoFresco window (replaces any pending request).”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
3 inputs, 1 required
- capabilitiesarrayrequired“Permissions to ask for: read (see the document and previews), edit (change documents, open/close tabs), export (files leave the editor), external-write (send d…”
- budget_creditsinteger“Credit budget for paid AI (required with spend)”
- reasonstring“Why, shown to the user (at most 200 characters)”
photofresco_documentsreads or searches
“Open documents in the PhotoFresco window: document_id, name, whether it is the active tab, revision, which agent controls it and whether it is paused.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
photofresco_attachdescribed as changing data
“Make this session target another open document by document_id (from photofresco_documents).”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
1 input, 1 required
- documentstringrequired“document_id to target”
photofresco_disconnectdescribed as changing data
“End this session (same as the user pressing Stop): in-flight work is interrupted, permissions are cleared, applied edits stay in History.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
1 input
- close_windowboolean“Also close the PhotoFresco browser window this server opened”
photofresco_list_tool_groupsreads or searches
“The op groups this server can list as tools, which are enabled, and how many tools each adds now.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
photofresco_select_tool_groupsdescribed as changing data
“Enable or disable op groups to change which PhotoFresco operations are listed as tools (sends tools/list_changed).”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
2 inputs
- enablearray“Groups to add”
- disablearray“Groups to remove”
adjust_addcreates or changes datadescribed as changing data
“Add a non-destructive adjustment layer above the active node.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
2 inputs, 1 required
- adjustment_typestringrequired“Which adjustment”
- paramsobject“Adjustment parameter patch.”
adjust_set_paramscreates or changes datadescribed as changing data
“Update the active adjustment layer’s parameters (same shapes as adjust.add).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
1 input, 1 required
- paramsobjectrequired“Adjustment parameter patch.”
canvas_resizecreates or changes datadescribed as changing data
“Change canvas size without resampling; content shifts by (dx, dy) px (e.g.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
4 inputs, 2 required
- widthnumberrequired“New width px”
- heightnumberrequired“New height px”
- dxnumber“Content shift x (default 0)”
- dynumber“Content shift y (default 0)”
crop_applycreates or changes datadescribed as changing data
“Apply pending crop or set a rectangle then apply.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
4 inputs
- xnumber“Document x”
- ynumber“Document y”
- widthnumber“Width”
- heightnumber“Height”

Show 26 more tools

doc_get_statereads or searches
“Get the full document state: document_id and content revision (agent sessions), dimensions, color mode, the layer tree (ids, names, kinds, blend modes, opacity, visibility, locks, pixel bounds), the …”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
doc_histogramreads or searches
“Return 256-bin histogram counts for the flattened visible document, restricted to the active selection when one exists.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- modestring“rgb, red, green, blue, or luminosity”
doc_newon 1 other servercreates or changes datadescribed as changing data
“Create a new document tab.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
8 inputs
- namestring“Document name (default Untitled)”
- widthnumber“Width in the selected unit”
- heightnumber“Height in the selected unit”
- unitstring“Measurement unit”
- resolutionnumber“Pixels per inch for physical units”
- backgroundstring“Background contents”
- background_colorarray“[r,g,b] when background=color”
- presetstring“Preset id for UI bookkeeping”
doc_sample_colorreads or searches
“Read the flattened composite color at document coordinate (x, y).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 2 required
- xnumberrequired“Doc x”
- ynumberrequired“Doc y”
edit_fillcreates or changes datadescribed as changing data
“Fill the selection (or the whole canvas if none) on the active layer.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
5 inputs
- contentsstring“color (default) or pattern”
- colorarray“[r, g, b] each 0-255”
- pattern_idstring“Pattern preset id; defaults to the active pattern when contents=pattern”
- blend_modestring“Pattern blend mode (default normal)”
- opacitynumber“Pattern opacity 0..1 (default 1)”
export_artifacton 1 other serverreads or searches
“Export the active document and keep the file in the editor as a retrievable artifact instead of starting a browser download.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
- formatstringrequired“png (flattened or one layer), psd (layered interchange) or pfd (native, full fidelity)”
- layer_idstring“PNG only: export this layer's own pixels instead of the composite”
filter_applydescribed as changing data
“Apply a destructive filter to the active layer (selection restricts it).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
2 inputs, 1 required
- filter_typestringrequired“Which filter”
- paramsobject“Type-specific parameters”
history_redoon 1 other serverdescribed as changing data
“Redo the next edit.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
Takes no inputs.
history_undoon 2 other serversdescribed as changing data
“Undo the last edit.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
Takes no inputs.
image_resizeon 7 other serverscreates or changes datadescribed as changing data
“Resample the whole document to new pixel dimensions (bilinear).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
2 inputs, 2 required
- widthnumberrequired“New width px”
- heightnumberrequired“New height px”
image_rotateon 3 other serverscreates or changes datadescribed as changing data
“Rotate the whole canvas by quarter turns: 1 = 90° clockwise, 2 = 180°, 3 = 90° counter-clockwise.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
1 input, 1 required
- turnsnumberrequired“1, 2, or 3 quarter turns”
layer_addcreates or changes datadescribed as changing data
“Add a new empty layer above the active node and make it active.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
1 input
- namestring“Layer name (default "Layer N")”
layer_deleteon 2 other serversdeletesdescribed as changing data
“Delete the active node.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
Takes no inputs.
layer_duplicateon 1 other servercreates or changes datadescribed as changing data
“Duplicate the active node (deep for groups); the copy becomes active.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
Takes no inputs.
layer_set_activecreates or changes datadescribed as changing data
“Set the active node (layers paint/transform; groups move as a unit).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
1 input, 1 required
- idstringrequired“Node id from doc.get_state”
layer_set_propscreates or changes datadescribed as changing data
“Set properties on a node (default: the active one).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
18 inputs
- idstring“Target node id (default: active)”
- namestring“Rename”
- visibleboolean“Show/hide”
- opacitynumber“0..1”
- blend_modestring“Blend mode”
- lockedboolean“Lock/unlock”
- lock_pixelsboolean“Raster layer pixel lock”
- lock_positionboolean“Raster layer position lock”
- lock_transparencyboolean“Raster layer transparency lock”
- clippedboolean“Clipping mask: confine rendering to the alpha of the layer below (⌥⌘G)”
- blend_ifobject or null“Raster layer Blend If {channel,thisLayer:[b0,b1,w1,w0],underlying:[...]}; null clears it”
- channel_maskobject“Raster layer RGB write mask {r:boolean,g:boolean,b:boolean}”
- knockoutstring“Knockout depth”
- blend_interior_as_groupboolean“Blend fill and interior effects as one source”
- blend_clipped_as_groupboolean“Apply the clipping base blend/opacity to the whole clip unit”
- transparency_shapes_layerboolean“Use source transparency to shape fill and interior effects”
- mask_hides_effectsboolean“Apply the raster layer mask to generated effect output”
- vector_mask_hides_effectsboolean“Apply the vector mask to generated effect output”
mask_addcreates or changes datadescribed as changing data
“Add a raster mask to the active layer.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
1 input
- modestring“Mask contents”
mask_removedeletesdescribed as changing data
“Delete the active layer’s mask (the layer becomes fully visible again).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
Takes no inputs.
render_maskreads or searches
“Preview a mask over a document-space region as a grayscale PNG (black 0 = hidden/unselected, white 255 = shown/selected) with exact coverage statistics { pixels, nonzero, full, mean } computed at doc…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
8 inputs
- xnumber“Left edge in document pixels (whole number, default 0).”
- ynumber“Top edge in document pixels (whole number, default 0).”
- widthnumber“Region width in document pixels (whole number; default: to the right canvas edge)”
- heightnumber“Region height in document pixels (whole number; default: to the bottom canvas edge)”
- max_sizenumber“Fit the preview inside this many pixels per side, never magnifying (default 1024).”
- scalenumber“Exact output pixels per document pixel (1 = actual pixels, 4 = 4× magnified with nearest sampling, 0.25 = area-averaged).”
- sourcestring“layer: the raster mask of layer_id (default); selection: the active selection”
- layer_idstring“Layer whose raster mask to show (source layer; default the active layer)”
render_previewon 14 other serversreads or searches
“Render the whole flattened composite to a PNG data URL, downscaled to fit max_size (never magnified).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- max_sizenumber“Max width/height in px (default 512, at most 2048)”
render_regionon 1 other serverreads or searches
“Preview a document-space region at a chosen scale as a PNG, without rendering the whole document.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
7 inputs
- xnumber“Left edge in document pixels (whole number, default 0).”
- ynumber“Top edge in document pixels (whole number, default 0).”
- widthnumber“Region width in document pixels (whole number; default: to the right canvas edge)”
- heightnumber“Region height in document pixels (whole number; default: to the bottom canvas edge)”
- max_sizenumber“Fit the preview inside this many pixels per side, never magnifying (default 1024).”
- scalenumber“Exact output pixels per document pixel (1 = actual pixels, 4 = 4× magnified with nearest sampling, 0.25 = area-averaged).”
- layer_idstring“Optional layer id (doc.get_state) to preview that layer alone instead of the composite”
selection_allcreates or changes datadescribed as changing data
“Select the whole document.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
Takes no inputs.
selection_ellipsecreates or changes datadescribed as changing data
“Select an ellipse inscribed in the given rect (doc coordinates).”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
6 inputs, 4 required
- xnumberrequired“Left”
- ynumberrequired“Top”
- wnumberrequired“Width”
- hnumberrequired“Height”
- modestring“How to combine with the existing selection”
- feathernumber“Feather radius in px (softens the edge)”
selection_invertcreates or changes datadescribed as changing data
“Invert the current selection.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
Takes no inputs.
selection_nonecreates or changes datadescribed as changing data
“Deselect — clear the selection so edits affect the whole canvas again.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
Takes no inputs.
selection_rectcreates or changes datadescribed as changing data
“Select a rectangle in doc coordinates.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
6 inputs, 4 required
- xnumberrequired“Left”
- ynumberrequired“Top”
- wnumberrequired“Width”
- hnumberrequired“Height”
- modestring“How to combine with the existing selection”
- feathernumber“Feather radius in px (softens the edge)”

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 38 tools
Says what it returns: 51% of 37 tools
States limits, defaults or errors: 10% of 21 tools
Says when to use it: 11% of 38 tools
Items covered per tool: 1.8 of 4 on average

Counted from the listing

Parameters with a description: 100% of 93
Tools with a description: 100% of 38
Typical description length: 631 characters

The tool set

Counted from the listing

Tools: 38
Size of the list: about 21,818 tokens for an agent to load (characters ÷ 4)
Naming: 38 of 38 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 38 of 38 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 MCP bundle is a file to install in a client that supports bundles, not a command.

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

Does the registry listing match what we found?

Feature #6

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

Registry says	We found	Result	Source · date
Published package can be started	Started and answered	matches	our test · 2026-10-23
Repository github.com/photofresco/photofresco-agent	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.photofresco
GitHub owner: an organization (photofresco)

Repository: github.com/photofresco/photofresco-agent
Stars: 0
Repository age: 0–30 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

4 of 5 record checks met · 4 do not apply

Not ranked by downloads: not an npm or PyPI package
Not ranked by stars: 0 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.
Does not applyPackage names its licence with a standard (SPDX) identifierNot an npm or PyPI package.
Does not applyThe version the registry lists can be installed and is not withdrawnNot an npm or PyPI package.
Does not applynpm package carries build provenance (attestation)PyPI packages have no npm-style attestation.
Does not applyNo known critical or high advisory in the package or its dependenciesNot an npm or PyPI package.

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.photofresco/photofresco

Answered from the data above

Is io.github.photofresco/photofresco safe to install?

We do not rate servers as safe or unsafe. 4 of its 5 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. 28 of its tools describe changing data (our AI model's reading of the descriptions). These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.

Is io.github.photofresco/photofresco free to use?

Its website (photofresco.com/) describes a freemium pricing model. This is an AI-classified reading of the page on 2026-10-23, so check the page itself before relying on it.

Has io.github.photofresco/photofresco been security tested?

Partly. 2 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.photofresco/photofresco do?

It lists 38 tools. In our AI model's reading of their descriptions (two runs had to agree, nobody checked it by hand), they include tools that read or search, create or change data, delete and control a browser or desktop. We did not call any tool, so this describes the text, not the behaviour.

Can io.github.photofresco/photofresco change or delete data?

28 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.photofresco/photofresco publish a security policy?

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

Where is the source code of io.github.photofresco/photofresco?

In github.com/photofresco/photofresco-agent, 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.DayuanJiang/next-ai-drawioNext AI Draw.ioalso has tools that controls a browser or desktop, creates or changes data, deletes, reads or searchescompare with this one
io.github.leancoderkavy/premiere-proMCP for Adobe Premiere Proalso has tools that controls a browser or desktop, creates or changes data, deletes, reads or searchescompare with this one
io.github.KyaniteLabs/mcp-videomcp-videoalso has tools that controls a browser or desktop, creates or changes data, deletes, reads or searchescompare with this one
io.github.gaopengbin/cesium-mcp-runtimealso has tools that controls a browser or desktop, creates or changes data, deletes, reads or searchescompare with this one
io.github.aadeshrao123/unreal-mcpUnrealMCP — AI Bridge for Unreal Engine 5also has tools that controls a browser or desktop, creates or changes data, deletes, reads or searchescompare with this one
io.github.wstierhout/ableton-live-mcpAbleton Live MCP Serveralso has tools that controls a browser or desktop, creates or changes data, deletes, 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: not run · nothing to check it against
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

2 exercised10 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). 2 of the 12 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.

Exercised · 2

1Inventory
tool-listReads the declared tools, resources and prompts.exercised
2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised

Not run, with the reason · 10

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
12Hidden content
audience-hidingChecks resources that hide content from the user.This check needs content the server returns, and nothing was read or 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)
172 msConnected after 0 redirects.
Read the inventory: 38 tools, 0 resources, 0 prompts.
1,244 msFinished: 2 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

freemium

read from photofresco.com/ · 2026-10-23

“Free forever · Works offline · Session recording & privacy”

Programming language

JavaScript

api.github.com · 2026-10-23

Hosting type

local package

registry · 2026-10-23

MCP capability

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

mcpb

registry · 2026-10-23

Freshness

0–30 days

registry updatedAt · 2026-10-23

Lifecycle status

active

registry · 2026-10-23

License class

does not apply

package ecosystem not queried by this layer (mcpb); only npm and PyPI are supported here

Integrity hash

does not apply

package ecosystem not queried by this layer (mcpb); only npm and PyPI are supported here

Signature / provenance

does not apply

package ecosystem not queried by this layer (mcpb); only npm and PyPI are supported here

Dependency advisories

not checked

only npm and PyPI packages are audited

Popularity

does not apply

package ecosystem not queried by this layer (mcpb); only npm and PyPI are supported here

Publisher signals

owner: an organization · repository age: 0–30 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.photofresco/photofresco: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/io.github.photofresco/photofresco

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.photofresco/photofresco)](https://protocolprobe.com/mcp/servers/io.github.photofresco/photofresco)

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