- run_workflow takes a gallery picture as its workflow (mcp_fill.opening
says what a name opens, for open_workflow too); a picture's workflow
opens with an id of its own, and the tab's mark goes into the workflow
before it loads, so ComfyUI finishing the tab does not drop it.
- With ComfyUI open in two browser tabs a task's actions were split
between them (one opened the task's tab, the other could not find it):
the page that did the last action gets the next first now, another
only when it is gone (mcp_bridge.py, pages keep an id of their own).
- describe_canvas on a big canvas: titles off, then nodes as a line each
with their settings, so every value stays readable.
- search_models names the models that did not fit; begin_task's tool
directory goes by name alone when the answer would be too long.
- ask_user refuses a "test" question with made-up options too.
- Exam round recorded: question 2 with nothing filed away, a big canvas
read right in 3 calls, question 3 in 12 calls.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- An answer past Antigravity's size is filed away unread (eight LoRA
searches in the exam): search_models answers small (loaders once,
four trigger words, a LoRA's author weight); describe_canvas gives a
big canvas's last nodes a line each; mcp_fit.py keeps any other list
answer within the size and names what it left out.
- An empty canvas: run_workflow, describe_canvas and get_situation say
to open a workflow first; get_image_info says a picture's workflow
opens with open_workflow.
- ask_user does not put a "test" question to the user; a task's picture
count counts what its runs made.
- AMB failed to load now and then: ComfyUI loads every file at once and
ui_ai_workbench.js set ui_ai_toolbox.js's sideHost before it was made
when the toolbox file ran first. Connected on first draw now;
tests/load_order.mjs runs every file first.
- input_facts moved to api/picture_mask.py to keep mcp_tools.py short.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
AMB only uses: training goes to its own plugin. This takes back the
record of what works (api/ai_evidence.py), the training network and
rounds (api/ai_training.py, ui_ai_network*.js, the round form), the
Gates' record switch, the ways' order by record and the external_skill
field of log_outside that only fed the record.
Kept, as part of using AMB:
- the user's word under a finished run, now only told to the AI
(ai_run_control.set_verdict, ui_ai_verdict.js);
- the Gates' "Custom nodes: only the ways'" rule;
- a picks block left to the AI takes its recommended picture.
Reverts 73518dc, 67bf5b2, 6647b05 and 49d05cf, then puts those three
back with tests in test_ai_run_watch, test_ai_gates and test_ai_panels.
Full suite and structure check pass.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The AI workbench's side column gets a training network view: base models
on the left, ways, skills and node packs on the right, a line for each
pair that ran, coloured by how it turned out (the user's word first, else
the AI's, dashed) and as thick as it ran often. A node or line shows its
record, last pictures and the pairs not tried yet in a card kept in sight.
"Start a training round" picks a skill (the AI's prompts with its advice
and without) or the ways of one use, up to four models and the pictures
each, and makes a task for the next AI (api/ai_training.py). Each run that
ends fills the trial it fits by what it used; the AI is told the next trial
and, once a model's trials are done, to compare them in a picks panel with
its own pick marked recommended. The record keeps the AI's pick apart from
the user's, and a picks block left to the AI takes its pick.
Tests: tests/test_ai_training.py; full suite and structure check pass.
Checked on an isolated ComfyUI: a round started from the view, four real
runs matched to their trials with the next one told each time, the
comparison panel and the user's pick reached the record and the graph.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
ai_sealed keeps a private task's prompt text and picture file names behind tokens ([P1],
[img1], task["sealed"]): mcp_server puts the texts back into a call's arguments for the tool
only, and ai_privacy.guard has every result masked on its way out (a node's STRING inputs
by ComfyUI's node list, prompt fields, picture names, any sealed text, also in the text
content). The user's own canvas changes are told sealed. A "prompts" panel block is the
user's prompt box (ui_ai_prompt_box.js): prompts, a negative one and reference pictures from
the gallery or dropped in, answered only from Anomalous, the AI getting tokens; above it the
prompt_pose skill's words for the canvas's model. A new private-only skill, privacy, tells
the AI how to work, and begin_task points a private task at it. Tests plant canary prompts
and picture names in every tool's result and check none gets out.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Each task has a lock in its header (task["privacy"]); the Gates window sets the default for
new tasks, and turning the default off pins the tasks it covered. mcp_server hands every
tool result to ai_privacy.guard last, after run pictures and the user's messages were
added, so a private task's image content never leaves; a call tied to no task is private
while the default is on or a private task is unfinished. The card in the AI app shows no
pictures for it, begin_task tells the AI, and turning it on or off is a user step and a
decision. A test calls every tool with a picture in its result and checks none gets out.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Gemini 3.8 Flash took seven exam tasks through Antigravity (107 calls, 19
failed, every task done). Nearly all failures were a tool's first use:
empty or guessed arguments. So:
- An argument error lists what the tool takes ("set_prompt takes: prompt
(needed), role, node_id, mode"), and the next call is right.
- One argument name per thing: set_prompt's text is prompt (as in
run_workflow), open_workflow's name is workflow (as in run_workflow).
- A wait over 55 s waits 55 s instead of failing; search_models takes a
model type in the singular too.
- An unread reply older than two hours no longer draws a new chat's calls
into its old task (a two-day-old mark took the first exam task).
The exam doc gets the setup, the Antigravity command line and the results.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Antigravity, Claude Code, Cursor and VS Code load tool descriptions on
demand themselves; looking tools up through Anomalous (tool_help, use_tool)
only doubled that: in one Gemini 3.8 Flash run 18 of 29 calls went to it,
while full-set chats had none. tool_help, use_tool, action_catalog.DAILY,
ai_gates.tool_set and the Gates row go.
An app still holding an older list is now told apart by the list it fetched
last (a fingerprint per app in anomalous/ai_tool_lists.json), so the note
under the task header also covers an Anomalous update.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- An AI app calling by an older tool list (tool_help or use_tool not offered,
use_tool for a tool offered directly, a tool the list lacks) is told so, and
the task header shows how to reconnect until the app fetches tools/list again.
- add_lora / set_model compare the base models on the model line
(model_advice.py; the page reports the line) and add base_model_note.
- get_model gives author_examples (sampler, steps, CFG, size, a LoRA's weight
from the Civitai record's example pictures) and the version name.
- run_workflow says ComfyUI's refusal as which node, what is wrong and the tool
that fixes it (run_refusal.py; mcp_run.js passes the refusal as data).
- Gates "When I don't answer": wait for me, or go with the recommendation once
the waiting time runs out (choices with a recommended option only), handed to
the AI in the same call and shown on the stage and under Decisions.
- A tool budget test (count, size, description length, required arguments) and
the exam tasks with their scorecard (docs/architecture/tool-exam.md,
tools/tool_exam.mjs). The tool set's text recommends Full for Antigravity.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The user took an option for something to select and then pressed "skip"
to confirm; boxes shown open read as fields to fill.
- Questions (stage panels, the strip over the message box): options are
buttons with an arrow under "One press sends it to the AI" and show the
pressed one at once; "Let the AI decide" moves to the question's top
right (the panel title for ask_user); a line of one's own is folded as
"None of these, I'll say it…". The Gates card folds its reason the same.
- A waiting task is one page: the sentence for the AI leads and sticks
under the task header while the page scrolls (the workbench measures the
header); "Say what to do" and the gallery are optional folds that say
how many pictures are in. The sentence has the AI do what the task says,
asking only when it says nothing. The Get started / Put ready tabs and
their words are gone.
- Gates window texts fixed (canvas covers building, lines are over the
message box, "Ask me" named as on the button); run_workflow waits up to
55 s by default, so a quick run comes back with its pictures.
- The UI map counts words the backend names (label_key) as used.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- The daily tool set now also offers tool_help and use_tool, and the
directory marks the tools reached that way; show_panel joins the daily
set. The "lazy" set is gone: a small model spent a third of its calls
looking tools up and never built what it planned.
- Gates window "Waiting for your answer" (1, 3 or 10 minutes): an open
question tells the AI to wait on with get_answers until then, and while
the user types (POST /anomalous/ai_tasks/{id}/typing) until a minute after
the last key. report and show_panel remind the AI to end each round with
ask_user; a question written in a note is pointed to ask_user.
- "Skip this one" is "Your call": the AI decides and does not ask again.
- ComfyUI's own `$$` widgets (the canvas image preview) are no longer
reported to the AI as the user's canvas change.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
When the user wrote to an older task while the AI had moved on, the AI's
next call (once its own task ended or paused) started a new task, where
report(reply_to=...) could not find the message. Now an app with no open
task goes back to the newest task of its own holding a reply it has not
read, and opens it again; an open task it is busy with stays. Naming the
calling app moves to api/ai_callers.py to keep ai_tasks.py under its size.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A third choice for "Tools for the AI" in the Gates window. With "On demand",
AI apps are offered only action_catalog.CORE plus two tools of
mcp_directory.py:
- CORE: begin_task, get_situation, run_workflow, run_status, report, ask_user,
get_answers.
- tool_help: the description and arguments of up to three tools named in the
directory.
- use_tool: calls any tool of the directory.
tools/list drops to 11 tools and about 9,000 characters (daily 22,200, full
40,700). With this set the directory begin_task brings names every tool and
says how to reach the ones not listed.
use_tool has no run of its own. mcp_server._call makes the call the tool it
names before anything else, so the user's gates, the timeline's step, the run
watch and the answer are all that tool's; the timeline never shows use_tool.
An unknown name, the card's own tools or wrong arguments come back as tool
errors that point to tool_help.
The default stays Full. Switching back to Daily or Full in the Gates window
undoes this without a revert, and this commit stands alone if it has to go.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
In the user's real tasks the AI spent many calls finding its way: reading the
canvas, searching node types, looking at combos and the activity log. The
directory gives it what ARCHITECTURE.md gives the code: each tool offered,
under its stage of the work, with its title. The stages are run, canvas,
models, prompts, combos, pictures, voices, the library, and the task and the
user. Seeing it, the AI can go straight to the tool it needs.
The directory is built from action_catalog's stages and the tool specs, so a
new tool shows up by itself, and a test checks that every stage has a heading.
It lists only the tools offered: about 1,100 characters for the daily set and
2,000 for the full one. begin_task's answer carries it, and so does
get_situation's while there is no task. The server's instructions and
begin_task's note point to it.
retext, the helper that rewrites a result's text from its data, moves from
ai_task_runs to mcp_tools, so both modules share it.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
In the user's real tasks, nearly every run ended with get_image_info, then
show_panel, then report: one extra call just to fetch the picture. The answer
that first tells the AI its run ended now carries up to four thumbnails of the
run's pictures (pictures_attached). That answer can be run_status, run_workflow's
own wait, or any other tool's answer.
It happens once per run. status() and news() mark the run when they first tell
its end, and show_pictures, called for every answer in mcp_server, attaches the
pictures to the marked run and clears the mark. Runs told of before this change
carry no mark, so they never bring old pictures along. The done `next` now says
to report with the pictures and to use a panel only to compare or ask. tell()
and show_pictures share _retext.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
In one real task the AI built an inpaint branch with 9 add_node and 16
connect_nodes calls. add_nodes takes the whole group in ComfyUI's API form, the
format models know best:
- links inside the group, and to canvas nodes as "#12", with outputs by slot
or name;
- a node's wire_to feeds canvas nodes the way add_node does.
All of it is checked before anything changes. The page lays the group out as
one block in a free spot (canvas_build.placedBlock) and applies it in one
transaction: one Ctrl+Z step, and a failure takes every new node out again
(applyWires now takes several nodes). The answer maps the AI's keys to node ids
and lists what is spliced and what is still unwired.
A splice now uses only an input that nothing else in the plan feeds. A node
whose latent comes from the group, or from wire_from, replaces the sampler's
empty latent instead (replace:true) rather than being fed twice. It is in the
daily tool set.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
GPT's auto-wiring (4afee83) was checked on the isolated test ComfyUI. A splice behind
a node, a new branch, the branch choice and the loop check each took one call. A
ControlNet still failed both ways, because its positive and negative have the same
type as a sampler's. A LoRA after a checkpoint wired only its MODEL line.
- Same-type sockets of the same name pair up (positive to positive).
- wire_to into an input that is already fed puts the new node in front: the old
source now feeds the new node's matching input. A ControlNet before a KSampler
is 6 links in one call; a LoRA before the sampler and both prompts is 5.
- insert_after splices every type a node passes through.
- add_node errors call the new node #new instead of #-1 and say how to pick sockets.
- frontend.md: the canvas_wiring paragraph moves from Verification to the
mutation rules.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Every chat began with 51 tools and about 43,000 characters of their
words, which a small model like Gemini Flash read half of before it
lost its way. The Gates window now offers either every tool or a daily
set of 19 (action_catalog.DAILY: runs of saved workflows with their
blanks, pictures, models and LoRAs, missing models, the task's own),
about 20,000 characters. tools/list follows the choice (ai_gates
tool_set, anomalous/ai_tools.json); calls are not limited by it, and an
app sees a change in a new chat. The window's rows share one builder.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A small model lost its way wiring the canvas: describe_canvas says what
feeds each input but not what is still free or what fits it, so it
looked up every node type and kept the graph in mind, and long answers
were filed away by Antigravity for the AI to open.
get_situation (mcp_situation.py) gives the task (what the user asked
last, what waits for them, decisions, pictures, steps outside AMB), the
canvas in brief (mcp_canvas_brief.js: a line per node, the inputs a run
needs that nothing feeds yet with the outputs that fit, ComfyUI's
errors), the latest run and the next step, kept under 3,600 characters.
add_node, connect_nodes and remove_nodes answer with what is still
unwired. The connect sentence, the rules and the instructions point a
new chat to get_situation first.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Anomalous sees only the calls made to it; an AI app's own commands and
scripts are invisible, and one rewrote a result six times. When the AI
calls, Anomalous now looks at the top of the output and input folders
for pictures no ComfyUI run saved and pictures rewritten in place since
its previous call (by the files' own times, bounded, never in the
background; new pictures wait while a prompt runs), shows them as an
"Outside AMB" step and tells the AI with its answer (ai_outside.py).
log_outside is the AI's own word on a command or script it ran.
The connect guide gains rules to paste into the AI app's own rules:
use AMB's tools, change pictures only by running workflows, ask and
explain in AMB, and say what was done outside it.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
In one hour Gemini ran 63 shell commands next to 23 AMB calls: checking files, cropping and
comparing parts of pictures, running OpenPose itself to see a skeleton, and painting pixels
with OpenCV (it overwrote an output picture six times).
- api/mcp_look.py zoom_image: part of a picture in the output, input or temp folder shown
larger, the same part of a second picture beside it; read only.
- get_image_info reads the temp folder too; run_status lists a run's PreviewImage pictures
(ai_task_runs.outputs_of(record, "temp"), kept as the step's previews, not its results).
- begin_task and the repaint note: AMB's tools cover looking; change pictures only by running
workflows, never by editing picture files with code of one's own.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- model_kind: Anima LLLite, Qwen-Image block-wise and Z-Image Fun ControlNets (and other
ModelPatchLoader files) go to model_patches, not controlnet; import and Tidy follow.
- api/mcp_model_use.py: search_models / get_model say which node types load each model, or
where a misfiled one belongs; move_model moves it there behind a new "files" gate (asks by
default, never overwrites).
- An empty drop-down in add_node says ComfyUI found no file; the task tab switch is no longer
logged as the user's canvas change.
- The folded task list stays while the pointer is in the box around its button and the list.
- The message box's picture button picks gallery pictures; "@" offers the gallery's newest and
searches it as you type.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Each run keeps its shape read from the prompt ComfyUI queued (ai_run_map.py): boxes by role
with their settings, typed links, plumbing wired through, and what changed since the task's
run before. The run step shows a one-line summary, the changes as chips and the boxes (top
down, fitted to the column, each locating its node); show_run_map puts it on the stage.
- By default the AI works in a tab of the task's own (ai_task_canvas.py, mcp_task_tab.js): the
open workflow is copied before its first change, the tab is brought back (a click on
ComfyUI's tab) before later changes, reads and runs, and the user's tab stays untouched.
Per-task switch in the header, default in the Gates window; the AI is told once.
- Output pictures can be handed to the task an AI is on (gallery card menu, the inspector's
✦), with the user's words: the AI gets them attached with what made them (ai_pictures.py).
search_images(with_pictures) attaches the first six.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- A stop button on a running run (timeline, and beside the run-status button), and stop_run for
the AI: only this run's prompts leave the queue or are interrupted; the step ends "cancelled"
and a user's stop reaches the AI as a "stop" message (ai_run_control.py).
- The run's progress carries ComfyUI's console since it began (the bar's note, models loading),
time left and per step, and VRAM; once queued, each sampler's working size is estimated from
the prompt, with warnings for an upscaled picture sampled again, a size past the card and a
huge decode, for the user and in the AI's run news (ai_run_watch.py, ui_ai_run_live.js).
- The materials picker opens as a side panel that leaves the page usable (the full-screen
browser makes room), expands to the large window and back, and remembers the choice.
- Esc closes the run-status card only (data-anomalous-escape).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
report takes reply_to, the id of the user's message or marks it answers:
the two steps point at each other and the timeline links them both ways
("Reply to step 2" / "The AI replied · step 4"). The AI's notes are laid
out (headings, lists, bold, code) by ai_text_format.js with textContent
only. The notice that brings the user's marks and messages, the report
description and the server instructions tell the AI to answer in
Anomalous, and to ask which fix with ask_user.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
ask_user shows a question in the AI workbench (options with an optional
recommended one, and unless other=false a line for an answer of the
user's own; no options: a line) and waits in the same call for the
answer, returning the choice or the text. Choices blocks gain
recommended and other; the step is named ask_user ("Asked you"). The
server instructions, begin_task and the workbench prompt tell the AI to
ask every question this way, never in its own chat.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
find_nodes looks up this ComfyUI's node types (inputs, outputs, choices)
from its own /object_info. new_workflow opens a new tab, blank or built and
laid out from a workflow in API form, never touching the open one;
add_node, connect_nodes, set_values and remove_nodes edit it. Everything is
checked against the nodes before the canvas changes (types, loops, settings,
choices with close matches); each is one Ctrl+Z step, logged as the AI's
and shown under its workbench step. Receipts now show rewiring ("wired":
what feeds an input, before and after). A run ComfyUI refuses reports
ComfyUI's own reason instead of "Prompt execution failed".
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The bar under a run shows a percent like ComfyUI's tab title (the running
node's steps, else the nodes done). While a run goes, every other tool answer
carries your_run with one sentence on where it stands, and the next answer
after it ends says so once (run_status telling it counts), so the AI need not
look in the output folder or at the screen.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- api/mcp_apps.py + api/mcp_app/task_card.html (MCP Apps, io.modelcontextprotocol/ui): apps that
support it (Claude, ChatGPT, VS Code…) show Anomalous's own card under begin_task, show_panel,
report and run_workflow results: the task's steps, latest thumbnails (inline), the AI's open
questions answered with a click (app_answer, plus a chat message so the AI goes on). The card
reads through app_task_view; both tools are for the card only (visibility "app"), are never
steps and never take the user's news. The card never answers a gate: an OK is only given in
Anomalous, so no tool an AI can reach grants one.
- api/mcp_prompts.py: prompts/list and prompts/get, four ready-made requests (slash commands):
workbench_task, pick_best, fix_missing_models, explain_canvas.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- api/ai_gates.py: changing the canvas, using the GPU, downloading and scanning online can each
go ahead, ask first or never (downloads ask by default; anomalous/ai_gates.json). A call that
asks waits on its step (state "asking", what it would do listed) up to 50 s for Allow or No
(with the user's reason for the AI); unanswered, the AI is told to wait and call again, the
later answer reaches it as a message, and the same call after an Allow goes ahead.
- ui_ai_gate.js: the card under a waiting step and the Gates window; a toast while elsewhere.
- ui_ai_flow.js + ai_task_view.flowStages: the task's stages in order, each done, running,
waiting or failed; a stage leads to its first step.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- api/action_catalog.py: every MCP tool's kind, stage of the work and gate in one place (a test
keeps it and the tools in step); steps now carry their stage.
- api/ai_task_changes.py: changes the user makes in Anomalous while an AI works become steps of
its task, reach the AI once with its next call (kind "change": keep it), and the activity
entry names the task; the activity page links to it ("AI task ->").
- api/ai_task_runs.py: run watching moved out of ai_tasks.py (600-line rule); a step a restart
left "running" is marked stopped when the record is read again.
- Pictures: inspector / compare with canvas / keep as tools on hover instead of three buttons
under every picture; tick any two (any step or task) and compare from the bar at the foot of
the page; the results strip shows thumbnails again.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A box under a task's timeline sends the user's message (POST
/anomalous/ai_tasks/{id}/message), kept as a 'user' step; get_answers now
also brings the user's messages and, with no panel named, waits for one.
The step says whether the AI has seen it; when the task has ended the box
says to ask in the AI app. The task list is grouped by day with an icon
for where each task stands.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A new rail page keeps each MCP call as a step of a task (api/ai_tasks.py,
one file per task in the user folder, the newest 300): named by the AI
with the new begin_task tool, else one app's calls without a long pause.
A step keeps what it did and what it made (models, the combo, the canvas
change by its activity entry, the pictures a run made, watched in the
history until it ends, spoken audio, scans); the new report tool leaves
the AI's notes and pictures it made another way. The page shows the tasks
and one task's results strip and timeline with links (picture viewer,
model page, combo, find or undo on the canvas, audio), updates live, and
gives the rail a dot while you are elsewhere; Home lists the last tasks.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
MCP now uses local_guard.is_local (one local check). A backup upload
request that is no upload answers 400 instead of 500. tests/test_local_guard.py.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The second batch of MCP tools: they change things, through the same code the UI uses.
- Canvas, done by the open ComfyUI page: describe_canvas, set_prompt, set_model,
add_lora, place_combo, check_workflow_models, fix_workflow_models, run_workflow,
open_in_anomalous. api/mcp_bridge.py sends the action over ComfyUI's websocket and
waits; web/modules/mcp_bridge.js claims it (visible tab first), does it with
Anomalous's canvas code and answers. Each change is one Ctrl+Z step, shows a toast and
is logged as the AI's (activity entries carry via: "mcp", with their undo).
- This server: scan_models (new / look up again / picked models, via /anomalous/scan_all),
list_voices and speak (Anomalous TTS through /prompt and /history).
- graph_splice.js takes the chain's slot types, so a LoRA can go into a model-only (UNet,
Flux) chain as LoraLoaderModelOnly; the default (MODEL and CLIP) is unchanged.
- Nothing deletes or renames files; acting tools are not marked read-only, so AI apps
ask before calling them.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
An MCP endpoint (Streamable HTTP) inside ComfyUI's server, so Claude, Cursor, Cherry
Studio and other MCP apps can ask about the user's library without anything extra
installed and without memory or VRAM while nobody is connected.
- api/mcp_server.py: one JSON-RPC message per POST, answered with JSON. Serves the
2026-07-28 stateless protocol (headers must match the body) and the earlier
initialize-based versions; no sessions. This computer only: loopback peer, no proxy
headers, loopback Host and Origin (DNS rebinding).
- api/mcp_tools.py: 11 read-only tools: library overview, model search and details
(optional cover), scan status, output-image search and generation settings
(optional thumbnail), combos, workflow recipes, saved prompts, generated audio,
activity log. Ids resolve inside their roots; tool failures come back as isError.
- docs/guides/mcp.md: setup for each app, what can be asked, privacy note.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
