Valmera MCP Tools: Catalog, Inputs & Workflow Limits

Public MCP Catalog — 134 Tools

Public server-card names are shown below. Check tools/list in your authenticated client for its schemas and descriptions. Open the machine-readable server card.

Use the Tools in a Reviewable Workflow

1. Connect and inspect. Follow the setup guide, authenticate, and inspect the client's tool schemas.
2. Select the project. Confirm the project identity, asset readiness and version. A file attached to a chat is not automatically uploaded to Valmera.
3. Read relevant evidence. Locate the words, shots or assets for the request. Check whether each next tool expects source or output time.
4. Apply a specific change. Keep the requested correction narrow enough to review. Check the returned state and any job identifier.
5. Follow and review. Observe the same job until its status is established. Inspect the returned preview, affected boundaries, captions and audio.
6. Finish in Studio. Select the accepted version, create its final MP4 and inspect the complete downloaded file. See final delivery.

Example correction brief: “In this project's selected version, inspect the caption at preview 00:05.2. The recording says Valmera. Correct the spelling, preserve the accepted cuts and music, and show the revised preview.” This is an illustrative request, not a reported tool execution. See caption text and timing and the two timeline clocks.

Session & project

Select the project, complete uploads, inspect state and follow long-running work. Confirm the returned project and version before applying changes.

list_projects

List your Valmera projects.

open_project

Select a project for the connected session. Confirm its identity in the returned state before editing.

create_project

Create a new project — from a video you are about to upload, or as a canvas project built purely from images, clips and music with no main video at all.

project_state

Where the project stands: indexing progress, current edit version, assets, and the latest rendered preview.

upload_start

Begin an upload and get the presigned destination for the file.

upload_finish

Finish the presigned upload workflow. Check the response and indexing state; an accepted upload is not a ready transcript or finished edit.

index_status

How far the one-time analysis has got: transcript, silences, shots and the labeled frame tiles the agent reads.

make_shorts

Create candidate child clip projects using the supported source selections and context. Each child still needs its own editing, review and final delivery.

shorts_status

Read the state of a podcast-shorts project and the child edits it produced.

open_short

Open one child short so the connected model can edit that project directly.

wait_for_job

Wait for the identified long-running operation and inspect its status or result. An observation timeout does not prove failure; follow the same job before restarting work.

download_url

A time-limited URL for a review preview, or for a Studio/Shorts final that already exists. It cannot create a final export.

watch_video

Request the available review or handoff for a rendered asset. Check what the client actually displays; a returned link is not evidence that a person watched it.

Reading the footage

Use transcript, frame and audio evidence to locate relevant material. Source time and edited-program time are different clocks; check which one each tool expects.

get_video_info

Read source metadata and a summary of available indexing and edit information.

get_transcript

Sentence-level transcript with timestamps for a range of source time.

get_words

Read word timestamps for a source-time range. Listen to the surrounding speech when choosing a cut.

get_kept_transcript

Inspect the words retained by the current edit in program time, including available repeated-phrase findings. Compare with the intended meaning.

search_transcript

Find where something is said, by substring and fuzzy match over sentences.

get_shots

Read detected shot boundaries. Use frames to assess whether a boundary is appropriate for the intended cut or transition.

find_silences

Find detected pauses meeting the requested conditions. Review the surrounding words before removing them.

get_audio_analysis

Measured musical and energy analysis of the source audio: tempo with a confidence figure, beat grid, and energy over time.

suggest_emphasis

Candidate emphasis words taken from the real transcript — the most vocally stressed words, words with digits, and rare terms.

list_assets

Every file in the project: uploaded clips, images, music and generated media.

get_edl

Read the edit decision list and version, including identifiers for supported changes.

look_at

Ask a vision model about frames from a range of the main video — for taste and visual questions the transcript cannot answer.

look_at_asset

Ask a vision model about frames from an uploaded clip or image, to choose which moment of a piece of b-roll to actually use.

Cutting

Change the kept footage in the selected version, then review joins and meaning. A local range change can affect later timing, so inspect the resulting edit.

cut_silences

Request cuts at detected pauses. Review sentence joins, pacing and words at each changed boundary.

remove_filler_words

Request removal of detected filler words and supported custom terms. Check the result for misses, clipped speech and changes to meaning.

cut_range

Remove a source-time range from the kept footage. Inspect the changed join and later timing.

restore_range

Restore a source-time range to the kept footage and review the resulting order and timing.

keep_segments

Replace the keep list for a broader restructuring. Inspect whether the change restores previously removed material.

beat_align_cuts

Slide each internal cut onto the nearest musical beat, within a tolerance. Never moves the program's first start or last end.

reset_edit

Reset the edit according to the current tool schema. Confirm the intended project and preserve the version you may need to revisit.

Captions & on-screen text

Transcript captions, authored text and text styling have different inputs. Caption corrections do not change what the speaker said.

add_captions

Create burned-in captions from transcript words or supported authored items. Request a named preset, bundled font, placement and emphasis, then review wording, timing and readability.

set_caption_fixes

Replace displayed transcript-caption spellings with the same number of words on each side. This differs from editing a selected transcript sentence in Studio.

audit_captions

Inspect reported caption coverage, timing and layout conditions. Review the cited moments in rendered output; the audit does not certify transcription accuracy.

set_caption_style

Change supported appearance settings on the caption track. Review wrapping, placement and animation after the change.

set_caption_mutes

Hide transcript captions over specified windows. Check the required clock and whether relevant speech remains adequately represented.

add_text

Burn a designed motion-graphics text template over a window of program time: title, subtitle, lower third, callout, big number, quote or chapter.

remove_text

Remove one text element by id.

add_title_card

Cut to a standalone full-frame card showing only this text, then return to the footage.

add_color_screen

Cut to a full-frame solid or gradient colour screen for a beat, then return.

add_corrupt_screen

Cut to a full-frame glitch or datamosh screen for a beat — a hard transition between sections.

Audio

Work with the source soundtrack and added music, voiceover or sound effects. Review the actual mix. A downloadable track or source-supplied license label does not by itself establish publication rights.

find_song

Find candidate links for a specific named song. Confirm the intended recording and usage rights; search results are not a license grant.

separate_music

Rebalance speech/vocals and other sound in the original recording. Separation can leave bleed or artifacts; listen before accepting it.

remove_stem_mix

Return from stem balancing to the original mixed soundtrack and review the result.

add_music

Add and mix a selected music asset. Review gain, timing and ducking against the speech instead of assuming the defaults fit.

swap_music

Replace the track of an existing music item while keeping its position, level and fit.

set_music_fit

Retime or refit existing music in place — start later, run to the end, fade out, loop, stop ducking.

remove_music

Remove one music item by id.

extract_audio

Extract sound from a supplied video into an audio asset. This does not separate speech from music already mixed together.

search_sfx

Find recorded sound-effect candidates with available source and rights metadata. Review the selected result and its terms before use.

fetch_sfx

Fetch a selected recorded sound effect and place it according to the available schema. Check the result and duration.

add_sfx

Place an uploaded sound effect in the program and review its timing and level.

move_sfx

Retime an existing sound effect, keeping which sound and how loud.

remove_sfx

Remove one sound effect by id.

add_voiceover

Lay an uploaded audio file over the program from any position, optionally ducking everything else under it.

remove_voiceover

Remove one voiceover by id.

set_audio_gain

Change the loudness of an existing music, sound-effect or voiceover item without re-adding it.

set_volume

Volume automation on the original footage's audio — the speaker — over a source-time span, down to a silent floor.

set_master_loudness

Apply the supported final-mix loudness treatment. This does not by itself repair an incorrect voice/music balance or prove every destination requirement is met.

Motion, speed & framing

Change framing, speed and visual movement, then inspect important subjects and timing throughout the affected range.

add_zoom

Zoom on a range of the finished edit — punch, ease, push-in or pull-out — aimable at any point of the frame.

remove_zoom

Remove one zoom by id.

add_zoom_path

Create a path through specified framing points. A keyframed path is not automatic tracking of every moving subject.

remove_zoom_path

Remove one travelling zoom by id.

punch_in_on_emphasis

Add punch zooms using available emphasis evidence. Inspect whether the chosen words and framing suit the clip.

set_speed

Change the playback speed of a source-time span. Review speech, picture and the timing of captions, music, covers and other elements afterwards.

remove_speed

Remove one speed span by id; that footage returns to normal speed.

set_frame

Set the output aspect ratio for every render: source, 16:9, 9:16, 1:1 or 4:5, by crop, pad or blurred pad.

auto_reframe

Use sampled frame evidence to choose a crop for the output shape. Review the whole result; this is not a guarantee of continuous subject tracking.

add_aspect_shift

Change aspect ratio mid-video, smoothly — go vertical for one section and back.

remove_aspect_shift

Remove one mid-video aspect change by id.

set_transitions

Transitions at scene changes — junctions where the footage genuinely changes shot, or where an insert splices in. Applying an effect at every jump cut inside one continuous take is the wrong default, so it is not the default.

set_fades

Fade from black at the start and to black at the end, picture and sound together.

Colour & finish

Grades and finishing effects change the picture. Review their combined appearance rather than treating a preset as proof of better quality.

set_color_grade

Apply a grade preset to the whole video: vibrant, warm, cool, black and white, vintage or cinematic.

set_grade_custom

Continuous exposure, contrast, saturation, temperature and tint, applied after the preset so the two compose.

add_stylize

Layer a windowed finishing effect: film grain, vignette, glow, chromatic aberration, dream blur, VHS, flash or camera shake.

remove_stylize

Remove one stylize effect by id.

apply_look

One call for a whole aesthetic — composes caption preset, grade, custom grade, transitions, fades and stylize into a single version.

Bringing media in

Inserts add scenes; overlays cover existing program time. Confirm the destination, asset and duration before changing the sequence.

start_media_sequence

Start a media-only sequence from an uploaded image or clip, replacing the current program. Add subsequent scenes with supported insert tools; check project and version first.

insert_media

Splice a clip or image into any position in the finished edit. Mid-take positions split the take around it.

remove_insert

Remove a selected insert and review the new timing of the surrounding program.

add_overlay

Draw an image or video over the program picture for a window of time — picture-in-picture, a corner logo, or a full-frame cover.

move_overlay

Reposition, retime or resize an existing overlay.

remove_overlay

Remove one overlay by id.

fetch_url

Download media from a link the user gave you — a video, a song or an image — and save it as a project asset.

search_stock

Search a stock library for b-roll you do not have, at the project's aspect ratio.Requires a stock provider key; hidden from the registry when unconfigured.

add_stock_media

Download one stock search result into the project, choosing the smallest rendition that still covers the output frame.Requires a stock provider key; hidden from the registry when unconfigured.

find_footage

Find candidate visual material relevant to the brief. Review identity, source rights, format and intended placement before use.

Repair & censoring

Pixel repair creates replacement imagery; a censor places a visible cover. Neither operation establishes complete removal of identifying information.

find_burned_text

Measure where text is burned into the footage — subtitle bands, watermarks, handles, on-screen labels — by reading the actual frames rather than estimating a rectangle.

erase_burned_text

Locate and repaint supported burned-in text regions. Inspect for remaining text, artifacts and changes to nearby detail.

erase_region

Request replacement imagery within a region. It can leave artifacts and does not recover verified historical detail behind the removed object.

remove_erase

Remove a selected repair treatment and inspect the resulting version or derived media.

blur_region

Cover a fixed rectangle in source-frame coordinates with blur, mosaic or solid black. Optional time windows use output time; recheck after cuts, speed changes or inserts. The rectangle does not track a moving subject.

remove_blur

Remove one censor region by id, or all of them.

Screen recordings & web demos

Capture a supported website or use an uploaded screen recording. Review the captured content, timing and resulting edit.

record_website

Record a live web page as video at the project's aspect: opens the URL, holds the top, smooth-scrolls to the bottom.

record_website_demo

Record a browser actually using a site — a visible cursor, real clicks and typing, captured with true timestamps.

showcase_demo

Place a screen recording and cut it like a product video in one call: splices the clip in, then puts a zoom on each click.

enhance_cursor

Apply supported pointer enhancement to a screen recording. Inspect detection, movement and any artifacts in the resulting video.

remove_cursor_enhance

Remove the cursor-enhancement treatment and review the restored source appearance.

set_screen_frame

The floating rounded window on a gradient — the standard treatment for a screen recording or app demo.

remove_screen_frame

Remove the floating window; the picture goes back to full-bleed.

Rendering & asking

Follow render progress and inspect the returned result. A job identifier, tool reply or sampled review is not a completed deliverable.

render_preview

Request the available preview or rendered review evidence for the selected edit. Inspect the returned asset and any job status before treating the preview as complete.

ask_user

Ask for a missing choice or clarification through the client-supported interaction. Inspect the response before work that depends on it.

Sources and Scope

The saved public catalog was checked on 2026-09-06. The page validates names and counts before displaying a refreshed card; an unavailable or inconsistent response uses the dated snapshot. Public metadata does not establish authentication, job success or client display behavior.

The MCP tools specification describes tool discovery, schemas and calls. Use Valmera's public server card, upload requirements, caption workflow and final-export guide for product details. Under the checked public contract, final creation remains in Studio. No authenticated media job was run for this reference update.

Frequently Asked Questions

Connect an Assistant to Valmera

Create an account, connect a compatible client and inspect the available tools. AI indexing and editing require paid access; review the result and create the final in Studio.