Crela
NPM · @CRELA/MCP · 2 COMPONENTS
Search the Crela software marketplace and publish, update and review your software from your agent.
Available components
Last scanned (13 hours ago)
Scores higher than 41% of npm servers
Category E-commerce
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security81
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known high-severity CVE affects zod 3.25.76, a direct dependency. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- 31 of 93 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency19
- Repository check failed: no source repository is declared. See how to fix → View diagnostics → Fail
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 1 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability59
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 5898 tokens (~327/item across 18 items; 18 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage93
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 78% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 18 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Checks we ran (15)
- Malware scan
- Known CVEs
- Install scripts
- Dependency health
- Source repository
- Provenance
- License
- Maintenance
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Checks we could not complete (1)
These are gaps on our side, not findings about this package. We only credit what we can confirm, so a category made up entirely of them scores 0.
- Security disclosure in Provenance & TransparencySecurity-disclosure policy not yet verified: we couldn't inspect the source repository.
Does not apply to this package (2)
- Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
- Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 21 Nov 26 0
- Stability: 0.97 → pass security
- 20 Nov 26 0
- Stability: pass → 0.97 functional
- 16 Nov 26 +15
- Stability: pass → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Malware scan: unverified → pass ▲ security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Package version: 1.9.0 → 1.10.1 functional
- 15 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- Known CVEs: fail → unverified ▼ security
- Stability: fail → pass ▲ security
- Dependency health: 0.85 → unverified ▼ functional
- Package version: 1.7.1 → 1.9.0 functional
- Package version: 1.7.1 → 1.8.0 functional
- 14 Nov 26 +15
- Malware scan: unverified → pass ▲ security
- 13 Nov 26 +1
- Malware scan: unverified → pass ▲ security
- Package version: 1.7.0 → 1.7.1 functional
- 12 Nov 26 −15
- Malware scan: pass → unverified ▼ security
- Stability: 0.90 → fail ▼ security
- Package version: 1.5.0 → 1.7.0 functional
- 10 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Analysed npm/@crela/mcp@1.10.1
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Vulnerabilities 1 finding
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-mrhx-c7xc-m3w5 | CVE-2023-54404 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
Background: What a vulnerability scan can and cannot prove →
Dependencies 93 packages
| Packages resolved | 93 |
|---|---|
| Stale | 31 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
check_review_status Check Crela review status ~321
Poll the lightweight review status of a submitted software (progress, sub-step, rate-limit budget). Returns { tool_id, tool_status, awaiting_media, missing_media, presentation, next_step, version, review_job_status, review_sub_step, review_passed, rejection_reason, review_started_at, review_completed_at, rate_limit }. awaiting_media true means the tool is approved but not listed yet because screenshots are missing (missing_media); upload them and it is listed on its own. presentation attests the listing: level "incomplete" (below the minimum of 2 screenshots), "minimum" (listed) or "ideal", with toward_ideal listing the concrete steps left (logo, 4 screenshots of at least 1280 px width, video). Aim for "ideal" before you stop. Polling: poll every 30 s until review_job_status is neither "queued" nor "running"; a full review takes 5-15 minutes. If review_passed is true: the tool is approved; it is listed as soon as awaiting_media is false. If review_passed is false after completion: call get_review_report for structured findings, fix the reported issues, then call update_software with the fixed build and poll again. Use get_review_report only after polling is done, not for live progress. Also shows rate_limit.updates_remaining_today so you know your budget before calling update_software, and rate_limit.window_resets_at shows when the update budget resets. Requires CRELA_API_KEY.
| Name | Type | Req | Description |
|---|---|---|---|
| software_id | string | yes | – |
No output schema declared.
No examples provided.
delete_media Delete a Crela media item ~99
Permanently delete a screenshot, logo or other media item from a software listing. Use get_my_software_details to get the media ids of uploaded files. Uploaded files (screenshots and logos) are also deleted from storage; video URL entries are only removed from the listing. Requires CRELA_API_KEY.
| Name | Type | Req | Description |
|---|---|---|---|
| media_id | string | yes | The id of the media item (from get_my_software_details response) |
| software_id | string | yes | – |
No output schema declared.
No examples provided.
delete_software Delete Crela software ~72
Permanently and irreversibly delete one of your software items. Only works if it has never been sold — sold tools cannot be deleted (buyers keep their claim); take those off the market with set_metadata { unlisted: true } instead. Requires CRELA_API_KEY.
| Name | Type | Req | Description |
|---|---|---|---|
| software_id | string | yes | – |
No output schema declared.
No examples provided.
get_my_software_details Get details of own Crela software ~162
Read the full metadata and media list of one of your own software items by software_id. Works for all statuses (pending, approved, rejected). Returns { tool, media, missing_media, presentation } where media lists all uploaded screenshots/images with their ids and sizes, and presentation attests the listing level (incomplete, minimum, ideal) with toward_ideal, the steps left to the ideal presentation. Use this to verify current state after set_metadata, to get media ids before calling delete_media, or to read current metadata before an update. Unlike get_software, this works with the internal software_id (not a public slug) and does not require the tool to be approved. Requires CRELA_API_KEY.
| Name | Type | Req | Description |
|---|---|---|---|
| software_id | string | yes | – |
No output schema declared.
No examples provided.
get_review_report Get Crela review report ~140
Fetch the full review report of a submitted software: pass/fail, rejection reasons and structured findings to fix. Heavier than check_review_status — call this only after the review pipeline has completed, not for live progress polling. Findings are capped at 10 locations each (a CVE finding can carry hundreds of near-identical ones); the response then sets truncated:true and locations_omitted per finding. Raise max_locations_per_finding when you actually need the long tail. Requires CRELA_API_KEY.
| Name | Type | Req | Description |
|---|---|---|---|
| max_locations_per_finding | integer | – | How many locations to keep per finding, default 10 |
| software_id | string | yes | – |
No output schema declared.
No examples provided.
get_sdk_marker Get the Crela SDK marker for an existing tool ~85
Fetch the per-tool SDK marker (KO-10) of an EXISTING tool by software_id. Embed it via the build env var CRELA_SDK_MARKER before uploading a new build with update_software. For a tool that does not exist yet use preview_marker (needs slug, not software_id). Requires CRELA_API_KEY.
| Name | Type | Req | Description |
|---|---|---|---|
| software_id | string | yes | – |
No output schema declared.
No examples provided.
get_software Get Crela software details ~60
Fetch the full public detail of one approved software item by its slug. Only works for publicly approved tools — use list_my_software to find your own tools by id.
| Name | Type | Req | Description |
|---|---|---|---|
| slug | string | yes | The software slug, e.g. "knowledge-editor" |
No output schema declared.
No examples provided.
get_submission_requirements Get Crela submission requirements ~301
Return the machine-readable submission rules (required fields, KO rules, bundle rules). Call this before submit_new_software so a build passes review. Public, no API key required. Recommended workflow for a new submission: 1. get_submission_requirements (this tool) → 2. preview_marker (paid tools only, embed CRELA_SDK_MARKER before building) → 3. precheck_build (dry-run gate check, catches problems before wasting a review slot) → 4. submit_new_software (creates the listing and starts review; pass the storage_path from step 3 to skip a second upload) → 5. upload_screenshot (at least 2 screenshots of at least 640 x 360 px; an approved tool is listed only once they are in. A square logo of at least 256 x 256 px is recommended; optionally upload_clip for a short MP4 preview clip) → 6. check_review_status (poll every 30 s until review_job_status is not "queued"/"running") → 7. get_review_report (read full findings after completion). For subsequent releases of an existing tool: 1. get_sdk_marker (paid tools: fetch current marker for the existing software_id) → 2. precheck_build → 3. update_software → 4. check_review_status (poll until complete). Never use submit_new_software for a tool that already exists.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_my_software List my Crela software ~114
List all software you own with its id, slug, review status (pending/approved/rejected/flagged), whether it is unlisted, price and sales count. Use this to recover the software_id needed by update_software, check_review_status, set_metadata and delete_software. Unlike search_software, this also returns pending, rejected and unlisted tools. Requires CRELA_API_KEY.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Max rows, default 50 |
| status | string | – | Filter by review status |
No output schema declared.
No examples provided.
precheck_build Pre-check a Crela build before submitting ~538
Dry-run the submit gate on a build ZIP WITHOUT creating a listing or a review. Runs the same deterministic checks as a real submission: framework detection, bundle completeness (required lockfiles/sidecars/manifests per framework x OS), the SDK marker KO-10 for paid tools, and the file-count limit. This is NOT the full review — it does not run virus/CVE scan, sandbox or the LLM agent. Does NOT count toward the 5/24 h rate limit. Call it as often as needed until gate passes. Response: { gate: "pass"|"fail", framework, platforms, entrypoint, sdk_marker: { required, satisfied }, code?, message? }. On fail: code and message explain exactly what to fix. On sdk_marker.satisfied=false: embed CRELA_SDK_MARKER in the build env and rebuild. Always call this before submit_new_software or update_software. The response also carries storage_path: pass that to submit_new_software or update_software instead of file_path and the same ZIP is not uploaded a second time. Requires CRELA_API_KEY.
| Name | Type | Req | Description |
|---|---|---|---|
| entrypoint | string | – | Override; auto-detected if omitted |
| file_path | string | – | Absolute path to the build ZIP on disk. Omit when passing storage_path. |
| framework | string | – | Override; auto-detected from the ZIP if omitted |
| license | string | – | Open source only: the SPDX identifier of the license, e.g. MIT, Apache-2.0, GPL-3.0-only. Omit it for the Crela Standard EULA. The product page then names the license, and it takes precedence over th… |
| platforms | array | – | Override; auto-detected if omitted |
| price_eur | number | yes | 0 for free, > 0 for paid. Paid tools require the embedded SDK marker. |
| slug | string | yes | The planned or existing tool slug (needed for the per-slug SDK marker check) |
| storage_path | string | – | storage_path from a previous precheck_build response - reuses that upload instead of sending the same ZIP again. |
No output schema declared.
No examples provided.
preview_marker Preview the Crela SDK marker for a planned slug ~110
Compute the per-tool SDK marker (KO-10) for a NOT-yet-created tool from its planned slug. Paid tools (price > 0) must embed this marker via the build env var CRELA_SDK_MARKER before building and submitting. For tools that already exist use get_sdk_marker (needs software_id, not slug). Returns { marker, slug, slug_available }. Requires CRELA_API_KEY.
| Name | Type | Req | Description |
|---|---|---|---|
| slug | string | yes | The planned URL slug of the tool you are about to submit |
No output schema declared.
No examples provided.
search_software Search Crela software ~216
Search the Crela marketplace for approved software, apps and games. Public, no API key required. Returns only approved, publicly listed tools — use list_my_software to see your own pending/rejected/unlisted tools. Use limit (1-50) to control how many results come through and keep the response small; page through the rest with page.
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | – | – |
| lang | string | – | Filter by the language of the software user interface, e.g. "de". Not the programming language. |
| limit | integer | – | How many results come through, 1-50 (server default 20). Lower it to a short shortlist to keep the response small; then get_software for the full detail of one. |
| page | integer | – | 1-based page for paging through more results (see total_pages in the response) instead of pulling everything at once |
| query | string | – | Full-text search over title and description |
| sort | string | – | Result ordering, default "latest" |
No output schema declared.
No examples provided.
set_metadata Set Crela software metadata ~1,147
Change metadata (title, description, price, categories, tags, etc.) of an existing software — no binary upload, no ZIP. DO NOT use this to upload a new build — use update_software for that. Changing title, description, long_description or categories on an approved tool triggers a re-review. Upgrading price_eur from 0 to a paid value also triggers re-review. All other fields (tags, price reductions, tool_languages, unlisted) do NOT trigger re-review. Set unlisted:true to take an approved tool off the market (reversible with unlisted:false) — existing buyers keep access, it just cannot be newly purchased. Rate limit: 5 updates per tool per 24 h (shared with update_software). check_review_status shows your remaining budget. Requires CRELA_API_KEY.
| Name | Type | Req | Description |
|---|---|---|---|
| age_rating | number | – | Games only, required before a game is listed (German JMStV). Send together with age_rating_source, age_rating_reasons and age_rating_questionnaire. For now Crela only offers games rated 0 (without an… |
| age_rating_questionnaire | object | – | Games only: answer every content question truthfully (true = the game contains it). Any true answer rules out age rating 0. |
| age_rating_reasons | – | – | Reasons for the age rating, e.g. "fantasy violence without blood"; required from 6 |
| age_rating_source | string | – | Where the age rating comes from: self (your own assessment), usk, pegi or iarc |
| categories | array | – | – |
| description | string | – | – |
| drm_mode | string | – | Paid tools are forced to sdk_required server-side regardless of this |
| framework | string | – | Usually auto-detected from the build; override only if wrong |
| install_type | string | – | installer, portable, zip or script |
| license | string | – | Leave it unset in almost all cases. An open source license (SPDX identifier) can only be set with the first submission; here only the unchanged value or an empty string (back to the Crela Standard EU… |
| long_description | string | – | – |
| max_devices | integer | – | Max simultaneous devices per license (1-10) |
| network_hosts | array | – | Hosts your app connects to, e.g. ["api.example.com", "*.cdn.example.com"]. A wildcard covers subdomains of your own domain only. Every host that receives user or device data must also be named in pri… |
| network_mode | – | – | Network allowlist mode: "none" = the app needs no network, "declared" = it only talks to the hosts in network_hosts, "user_chosen" = the user picks the servers (SSH, database, RSS or download clients… |
| platforms | array | – | Correct the platforms when the ZIP auto-detection got them wrong |
| price_eur | number | – | 0 for free, or at least 0.50 (the smallest amount our payment provider can charge) |
| privacy_policy | string|null | – | Privacy policy text; null clears it. KO_09 rejects a build whose code contacts an analytics or telemetry service that this text does not name - this is the only way to satisfy that rule. |
| safety_notes | – | – | Warnings and safety information buyers need, e.g. flashing lights or changes to system settings (plain text, max 2000 characters). Shown on the product page; null clears it |
| sale_ends_at | string|null | – | ISO timestamp when the sale ends; null = open-ended |
| sale_price_eur | – | – | Discounted price (at least 0.50 and below price_eur); null ends the sale. Buyers see the lowest price of the 30 days before the sale crossed out |
| security_updates_until | string | – | Date until which you provide security updates (YYYY-MM-DD), at least two years from today; five years recommended. Shown to buyers before they buy. Required for paid tools, optional for free tools. C… |
| software_id | string | yes | – |
| support_contact | string|null | – | Support contact shown to buyers, e.g. an email address; null clears it |
| system_requirements | string | – | – |
| tags | array | – | – |
| title | string | – | – |
| tool_languages | array | – | ISO 639-1 codes of every language the software user interface is available in, e.g. ["en","de"]; replaces the whole list. NOT the programming language - this drives the lang filter in search_software… |
| trial_days | integer | – | Trial duration in days (1-90) |
| trial_enabled | boolean | – | Enable a time-limited trial for a paid tool |
| unlisted | boolean | – | true = take off market (hidden, not purchasable); false = re-list |
| video_url | string|null | – | https YouTube/Vimeo link; null removes the video entry |
No output schema declared.
No examples provided.
submit_new_software Submit new software to Crela ~1,283
Submit a brand-new software listing to Crela and start its review. Use this only for the FIRST submission of a tool that has never existed before. DO NOT use this to upload a newer version of a tool that already exists — use update_software for that. Always run precheck_build first to catch gate failures before wasting a review slot. entrypoint, framework, platforms, os and arch are auto-detected from the ZIP - pass them only when detection is wrong or the server reports an ambiguous entrypoint. Returns { tool: { id, slug, ... }, tool_review_id, build_id: null, warnings? }. Use tool.id as software_id for check_review_status, update_software, set_metadata and all other subsequent calls. The review starts asynchronously — poll check_review_status until complete. Requires CRELA_API_KEY.
| Name | Type | Req | Description |
|---|---|---|---|
| arch | string | – | CPU architecture; default x86_64; x64/amd64 and arm64 aliases accepted |
| categories | array | yes | Required: 1 to 3 categories, the first is the main one. No default. |
| confirm_build_declarations | boolean | yes | Required for every build (Crela Creator Terms § 3 (5)). Set true only if all of this is true for the build: It does not update itself. No code, bundled program or script downloads, installs or runs n… |
| description | string | yes | Short description, min. 20 characters, no URLs |
| entrypoint | string | – | Path to the main binary inside the ZIP; auto-detected. Set it when the server reports the entrypoint is ambiguous (VALIDATION error with candidates). |
| file_path | string | – | Absolute path to the build ZIP on disk. Omit when passing storage_path. |
| framework | string | – | Override; auto-detected from the ZIP if omitted |
| license | string | – | Open source only: the SPDX identifier of the license, e.g. MIT, Apache-2.0, GPL-3.0-only. Omit it for the Crela Standard EULA. The product page then names the license, and it takes precedence over th… |
| long_description | string | yes | Long description, min. 80 characters, no URLs |
| network_hosts | array | – | Hosts your app connects to, e.g. ["api.example.com", "*.cdn.example.com"]. A wildcard covers subdomains of your own domain only. Every host that receives user or device data must also be named in pri… |
| network_mode | string | yes | Required (Crela Creator Terms § 3 (1)). Network allowlist mode: "none" = the app needs no network, "declared" = it only talks to the hosts in network_hosts, "user_chosen" = the user picks the servers… |
| os | string | – | Target OS of this build; derived from the detected platforms if omitted |
| platforms | array | – | Override; auto-detected if omitted |
| price_eur | number | yes | 0 for free, or at least 0.50 (the smallest amount our payment provider can charge) |
| privacy_policy | string | – | Privacy policy text. Required in practice for anything with analytics or telemetry: KO_09 rejects a build whose code talks to a tracking service that the policy does not name. |
| safety_notes | string | – | Warnings and safety information buyers need, e.g. flashing lights or changes to system settings (plain text, max 2000 characters). Shown on the product page |
| security_updates_until | string | – | Required for paid tools, optional for free tools (a free tool without it is listed as coming without a commitment to security updates). Date until which you provide security updates (YYYY-MM-DD), at… |
| slug | string | yes | URL slug; stored lowercase |
| storage_path | string | – | storage_path from a previous precheck_build response - reuses that upload instead of sending the same ZIP again. |
| support_contact | string | – | Support contact shown to buyers, e.g. an email address |
| system_requirements | string | yes | – |
| tags | array | – | – |
| title | string | yes | – |
| tool_languages | array | – | ISO 639-1 codes of every language the software user interface is available in, e.g. ["en","de"]. NOT the programming language. Defaults to ["de"] - set it deliberately, it drives the lang filter in s… |
| version | string | yes | Semver, e.g. "1.0.0". A first submission takes no pre-release suffix. |
No output schema declared.
No examples provided.
update_media Update a Crela media item ~174
Update a media item: the sort order of any item (lower sort_order appears first), or the URL of a video entry (https YouTube/Vimeo link only). url can only be changed for video entries; for screenshots delete and re-upload. This tool does not create entries: a video is added with set_metadata { video_url }, an image with upload_screenshot. Use get_my_software_details to get media ids. Provide at least one of sort_order/url. Requires CRELA_API_KEY.
| Name | Type | Req | Description |
|---|---|---|---|
| media_id | string | yes | The id of the media item (from get_my_software_details response) |
| software_id | string | yes | – |
| sort_order | integer | – | Display position; lower values appear first |
| url | string | – | New video URL (video entries only; https YouTube/Vimeo) |
No output schema declared.
No examples provided.
update_software Update existing Crela software with a new build ~619
Replace the build binary of an EXISTING software with a new version. Use this when a tool already exists and you want to ship a new release or demo build. DO NOT use this for a brand-new tool that has never been submitted — use submit_new_software for that. To change only metadata (title, price, description) without uploading a binary, use set_metadata instead. Use list_my_software to recover the software_id if you do not have it. Handles the presign → direct R2 upload → finalize flow, so large builds do not hit the upload timeout. Sending channel "release" puts the tool back into review; channel "demo" publishes a demo build without touching the live listing. Rate limit: 5 updates per tool per 24 h (shared with set_metadata); this tool checks the budget before uploading, so an exhausted quota costs you nothing. check_review_status shows the remaining budget. Pass the storage_path from precheck_build instead of file_path to avoid uploading the same ZIP twice. Requires CRELA_API_KEY.
| Name | Type | Req | Description |
|---|---|---|---|
| arch | string | yes | CPU architecture; x64/amd64 and arm64 aliases are accepted |
| change_message | string | – | Changelog note shown to buyers after approval |
| channel | string | – | Default "release" |
| confirm_build_declarations | boolean | yes | Required for every build (Crela Creator Terms § 3 (5)). Set true only if all of this is true for the build: It does not update itself. No code, bundled program or script downloads, installs or runs n… |
| entrypoint | string | – | Path to the main binary inside the ZIP; auto-detected if omitted |
| file_path | string | – | Absolute path to the build ZIP on disk. Omit when passing storage_path. |
| os | string | yes | – |
| software_id | string | yes | – |
| storage_path | string | – | storage_path from a previous precheck_build response - reuses that upload instead of sending the same ZIP again. |
| version | string | yes | Semver, e.g. "1.7.5". A pre-release suffix such as "1.0.0-beta.1" is allowed here. |
No output schema declared.
No examples provided.
upload_clip Upload a Crela preview clip ~179
Upload a short preview clip for a software from a local MP4 file. It plays muted when someone points at the card on crela.io, so show the app in use from the first second. MP4 with H.264 video, landscape 16:9 (at least 1280 x 720 px), 3 to 60 seconds, max 80 MB; 15 to 30 seconds work best. Crela hosts the clip itself and does not convert it: export it as H.264 MP4. A new clip replaces the old one. Use delete_media to remove it. A clip counts toward the ideal presentation (presentation.toward_ideal in check_review_status). Requires CRELA_API_KEY.
| Name | Type | Req | Description |
|---|---|---|---|
| file_path | string | yes | Absolute path to the MP4 file on disk |
| software_id | string | yes | – |
No output schema declared.
No examples provided.
upload_screenshot Upload a Crela screenshot ~278
Upload a screenshot or the logo for a software from a local file path. Valid types: "screenshot" (default) or "logo". Accepted formats: JPG, PNG, WebP or GIF, max 5 MB per image. Before a listing goes live it needs at least 2 screenshots of the real app (at least 640 x 360 px); the server rejects smaller images. The first screenshot doubles as the cover. A logo is recommended, not required: square, at least 256 x 256 px; without one the launcher shows the first letter of the title. The review approves the software on its own; an approved tool without the screenshots stays unlisted and is listed on its own after the upload. The response says what is still missing (missing) and whether the listing just went on the market (went_live). For the ideal presentation (logo, 4 or more screenshots of at least 1280 px width, a video) read presentation.toward_ideal from check_review_status. Use delete_media to remove an uploaded image, update_media to reorder. Requires CRELA_API_KEY.
| Name | Type | Req | Description |
|---|---|---|---|
| file_path | string | yes | Absolute path to the image on disk |
| software_id | string | yes | – |
| type | string | – | Media type: "screenshot" (default) or "logo" |
No output schema declared.
No examples provided.
How do I install the Crela MCP server?
Crela runs locally as an npm package, launched with npx -y @crela/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @crela/mcp
claude mcp add io-crela-mcp -- npx -y @crela/mcp
What is the Crela MCP server?
Crela is an MCP server listed in the public MCP registry as io.crela/mcp. Search the Crela software marketplace and publish, update and review your software from your agent. This page covers its npm package (@crela/mcp).
Is the Crela MCP server safe to use?
Crela scores 70 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 21 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Crela MCP server expose?
Crela exposes 18 tools: search_software, get_software, get_submission_requirements, list_my_software, precheck_build, and 13 more. Their descriptions and schemas cost roughly 5,898 tokens of context every time the server is loaded.
Is the Crela MCP server still maintained?
Crela is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the Crela MCP server under?
Crela declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.
What did VerifyMCP test on the Crela MCP server?
VerifyMCP ran 15 checks on Crela, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about Crela: Security disclosure. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.