Phoenix Labs
REMOTE · API.PHOENIXLABS.SPACE
Restore old video and turn images into clips with sound. Pay from a capped balance, by card or USDC.
Available components
Last scanned (19 hours ago)
Scores higher than 15% of remote servers
Reachable. Last reached 21 Nov 2026.
Category Design and Media
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security81
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- The endpoint enforces authorisation, advertised via RFC 9728 protected-resource metadata. View diagnostics → Pass
- HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement. View diagnostics → Unverified
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
- The authorisation server supports Client ID Metadata Documents, the current MCP client-registration mechanism. View diagnostics → Pass
Transport & Reachability0
- Transport blocked by authentication: the endpoint requires auth we don't have to verify streamable-http. See how to fix → View diagnostics → Unverified
Schema Quality & AI Usability0
- Schema blocked by authentication: the endpoint requires auth we don't have to read it. See how to fix → Unverified
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage0
- Tool coverage blocked by authentication: the endpoint requires auth we don't have to read its tools.Unverified
Tool Safety0
- Tool safety blocked by authentication: the endpoint requires auth we don't have to read its tools.Unverified
Capabilities0
- Capabilities blocked by authentication: the endpoint requires auth we don't have to read them. See how to fix → Unverified
Unverified: 6 categories
Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm. Claim this server and supply a read-only token to verify it and lift the score.
Checks we ran (4)
- TLS certificate
- Authorization
- HSTS header
- DNSSEC
Checks we could not complete (7)
These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.
- HTTPS in Endpoint SecurityHTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.
- Transport in Transport & Reachability (scores 0 for this)Transport blocked by authentication: the endpoint requires auth we don't have to verify streamable-http.
- Schema quality in Schema Quality & AI Usability (scores 0 for this)Schema blocked by authentication: the endpoint requires auth we don't have to read it.
- Stability in Stability & Change Management (scores 0 for this)Stability not yet verified: not enough scan history yet (needs a 30-day window).
- Tool coverage in Tool Coverage (scores 0 for this)Tool coverage blocked by authentication: the endpoint requires auth we don't have to read its tools.
- Tool safety in Tool Safety (scores 0 for this)Tool safety blocked by authentication: the endpoint requires auth we don't have to read its tools.
- Capabilities in Capabilities (scores 0 for this)Capabilities blocked by authentication: the endpoint requires auth we don't have to read them.
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
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.
- 6 Nov 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 29 Sept 26 0
- Endpoint reachability: reachable → behind authorisation ▼ security
- 28 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 27 Sept 26 0
First indexed and scored.
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 · Probed https://api.phoenixlabs.space/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=phoenixlabs.space | CN=WE1,O=Google Trust Services,C=US | 4 Oct 2026 | 2 Jan 2027 | ECDSA 256 | ECDSA-SHA256 | 818c07ca54cfb3670e8e1fa6492f24e3 |
| SANs: phoenixlabs.space, api.phoenixlabs.space, *.api.phoenixlabs.space | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of api.phoenixlabs.space. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| space. | DS published | 51168 | 13 | Verified |
| phoenixlabs.space. | No DS | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication Enforced and verified
The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.
| Result | Enforced and verified |
|---|---|
| Enforced | On connection |
| HTTP status | 401 |
WWW-Authenticate challenge Bearer resource_metadata="https://api.phoenixlabs.space/.well-known/oauth-protected-resource/mcp", scope="phoenix"
Bearer resource_metadata="https://api.phoenixlabs.space/.well-known/oauth-protected-resource/mcp", scope="phoenix" | Header | Value |
|---|---|
| www-authenticate | Bearer resource_metadata="https://api.phoenixlabs.space/.well-known/oauth-protected-resource/mcp", scope="phoenix" |
Protected resource metadata
| Document | https://api.phoenixlabs.space/.well-known/oauth-protected-resource/mcp |
|---|---|
| Retrieved | Yes |
| Resource | https://api.phoenixlabs.space/mcp |
| Authorisation server | https://api.phoenixlabs.space |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://api.phoenixlabs.space/mcp | Auth required | 401 | |
| http (plaintext) | http://api.phoenixlabs.space/mcp | Inconclusive | 405 |
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 →
cancel_job ~55
Cancel a restore or clip whose file was never uploaded, and get its price back on the balance at once.
| Name | Type | Req | Description |
|---|---|---|---|
| job_id | string | yes | A restore's job_id (cloud_…) or a clip_id (motion_…). |
No output schema declared.
No examples provided.
create_restore ~300
Start a cloud restore of an old video (tape, DVD, film scan, old phone clip): denoise, deinterlace, rebuild detail and upscale. Returns an upload_url; PUT the video there, then call start_restore. With an agent key it is paid from the balance now (pay_with 'balance'), and refunded to the balance if it fails. With pay_with 'checkout' (or no key) the user pays through a checkout link that start_restore returns. Up to 2 GB; standard up to 30 minutes, enhanced and studio_max up to 6 minutes.
| Name | Type | Req | Description |
|---|---|---|---|
| content_type | string | yes | The video's MIME type, e.g. video/mp4. |
| duration_seconds | number | yes | Length in seconds. The GPU checks it; a file much longer than declared is refused and refunded. |
| string | – | Needed for pay_with 'checkout': where the receipt goes. | |
| filename | string | yes | The video's file name, e.g. wedding-1994.mp4. |
| height | integer | – | – |
| pay_with | string | – | Default: balance when this connection has a key, otherwise checkout. |
| quality | string | – | standard: denoise, deinterlace, 2x upscale. enhanced: adds AI detail reconstruction, for badly degraded footage. studio_max: enhanced, delivered at up to 4K. |
| size_bytes | integer | – | – |
| width | integer | – | – |
No output schema declared.
No examples provided.
create_top_up_link ~73
A checkout link the user opens to add money to the balance (US$5 to $200). Nothing is charged until they pay.
| Name | Type | Req | Description |
|---|---|---|---|
| amount_usd | number | yes | Dollars to add, 5 to 200. |
| string | – | For the receipt, if the balance doesn't have one yet. |
No output schema declared.
No examples provided.
get_balance ~31
The Phoenix balance this key can spend: the balance, and this key's limit, amount spent and amount left.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_clip ~43
Status of a clip. When status is 'done', video_url plays it and download_url saves it (both valid 24 hours).
| Name | Type | Req | Description |
|---|---|---|---|
| clip_id | string | yes | – |
No output schema declared.
No examples provided.
get_prices ~30
Current prices and limits for Phoenix Motion clips and Cloud Restore, in US dollars. Free, no key needed.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_restore ~39
Status of a restore. When status is 'done', download_url is the restored video (valid 24 hours).
| Name | Type | Req | Description |
|---|---|---|---|
| job_id | string | yes | – |
No output schema declared.
No examples provided.
list_clips ~21
The most recent clips made with this key, newest first.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
make_clip ~207
Phoenix Motion: turn one still image into a five-second video clip at 24 fps, with sound made in the same pass, from a prompt describing the motion, camera and sound. Costs the listed price (see get_prices) from the balance; a clip that fails or is refused costs nothing. Pass image_url to start at once; otherwise PUT the image to the returned upload_url and call start_clip.
| Name | Type | Req | Description |
|---|---|---|---|
| content_type | string | – | Needed only when uploading instead of image_url. |
| image_url | string | – | Public link to a JPEG, PNG or WebP image, up to 20 MB. |
| loop | boolean | – | Seamless loop: only what the prompt names moves, and the clip ends where it starts. |
| prompt | string | yes | What moves, how, and what the camera and sound do. Up to 800 characters. |
| seed | integer | – | Reuse a clip's seed to get the same take again. |
| size | string | – | – |
No output schema declared.
No examples provided.
quote_restore ~126
Exact price in US dollars to restore one video clip in the cloud, from its length and resolution. Free, no key needed.
| Name | Type | Req | Description |
|---|---|---|---|
| duration_seconds | number | yes | Length of the clip in seconds. |
| height | integer | – | Frame height in pixels, if known. |
| quality | string | – | standard: denoise, deinterlace, 2x upscale. enhanced: adds AI detail reconstruction, for badly degraded footage. studio_max: enhanced, delivered at up to 4K. |
| width | integer | – | Frame width in pixels, if known (default: standard definition). |
No output schema declared.
No examples provided.
start_clip ~32
After uploading the image to make_clip's upload_url: start making the clip.
| Name | Type | Req | Description |
|---|---|---|---|
| clip_id | string | yes | – |
No output schema declared.
No examples provided.
start_restore ~54
After the video is uploaded: starts a balance-paid restore on the GPU, or returns the checkout_url the user must open to pay for a checkout restore (it starts once they have paid).
| Name | Type | Req | Description |
|---|---|---|---|
| job_id | string | yes | – |
No output schema declared.
No examples provided.
top_up_with_usdc ~121
Add money to the balance by paying USDC on Base yourself, with x402 (for assistants that hold a crypto wallet). Call it without a payment to get the payment requirements back (an x402 PaymentRequired error), sign the EIP-3009 transfer, then call it again with the signed payment in _meta['x402/payment']. $1 to $200; 1 USDC adds $1. No gas needed: the facilitator pays it.
| Name | Type | Req | Description |
|---|---|---|---|
| amount_usd | number | yes | Dollars to add, 1 to 200. |
No output schema declared.
No examples provided.
How do I install the Phoenix Labs MCP server?
Phoenix Labs is a hosted endpoint at https://api.phoenixlabs.space/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · api.phoenixlabs.space
claude mcp add --transport http thekillsquad007-phoenix-labs 'https://api.phoenixlabs.space/mcp'
What is the Phoenix Labs MCP server?
Phoenix Labs is an MCP server listed in the public MCP registry as io.github.thekillsquad007/phoenix-labs. Restore old video and turn images into clips with sound. Pay from a capped balance, by card or USDC. This page covers its hosted endpoint (https://api.phoenixlabs.space/mcp).
Is the Phoenix Labs MCP server safe to use?
Phoenix Labs scores 32 out of 100 on VerifyMCP. 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 Phoenix Labs MCP server expose?
Phoenix Labs exposes 13 tools: get_prices, quote_restore, create_restore, start_restore, get_restore, and 8 more. Their descriptions and schemas cost roughly 1,132 tokens of context every time the server is loaded.
Does the Phoenix Labs MCP server require authentication?
Yes. Phoenix Labs asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.
Is the Phoenix Labs MCP server still maintained?
Phoenix Labs 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 did VerifyMCP test on the Phoenix Labs MCP server?
VerifyMCP ran 4 checks on Phoenix Labs, covering TLS certificate, Authorization, HSTS header and DNSSEC. 7 items could not be completed, a gap on our side rather than a finding about Phoenix Labs: HTTPS, Transport, Schema quality, Stability and 3 more. 6 categories score 0 for that reason, because we only credit what we can confirm. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.