Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

GravityPort

NPM · GRAVITYPORT-MCP

Built into the GravityPort desktop app: install it, then Claude or Codex can search your AI library.

Available components

0 this week 64 Trust /100

Last scanned (16 hours ago)

Scores higher than 37% of npm servers

Category Design and Media

Trust breakdown (7 categories)

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 Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency35
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
  • License check failed: the license (PolyForm-Shield-1.0.0) isn't a recognized OSI-approved license. See how to fix → Fail
  • Actively maintained (last published 3 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability60
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 3037 tokens (~121/item across 25 items; 25 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 Management0
  • Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage76
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 27% 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 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 26 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

Unverified: 1 category

A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

What we tested

Checks we ran (15)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • 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.

  • Stability in Stability & Change Management (scores 0 for this)Stability not yet verified: not enough scan history yet (needs a 30-day window).

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 →

Changelog

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.

  • 13 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 12 Nov 26 49

    First indexed and scored.

Diagnostics

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/gravityport-mcp@0.3.12

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 →

Dependencies 0 packages
Packages resolved 0
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 25 exposed · ~2,969 tokens

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 →

Tool Tokens
asset_attach_prompt ~36

Attach or replace the full prompt recipe for a saved asset.

NameTypeReqDescription
assetIdstringyes–
promptstringyes–

No output schema declared.

No examples provided.

asset_create ~390

Copy an image into the GravityPort library and save prompt recipe metadata. The image path must be an absolute path on this machine. Symbolic links are rejected. Only supported image and video formats are imported. Identical bytes already in the library (outside Trash) return the existing asset with deduplicated: true instead of creating a copy.

NameTypeReqDescription
business_fieldsobject–Stored with the asset but not searchable; put anything that should be findable via search into tags instead.
categorystring–Category label shown in the app.
favoriteboolean–Mark the asset as a favorite.
groupstring–Group the asset is filed under; grouping, not a project.
imagePathstringyesAbsolute path of the image on this machine.
negative_promptstring––
parent_asset_idstring––
promptstring––
ratinginteger–Star rating from 0 (unrated) to 5.
ratiostring––
referencesarray––
skillstring––
sourceobject–Optional generation provenance, such as generation_tool, model, codex_session_id, or codex_thread_id. The original image path and Codex task ID are detected automatically.
sourceTypestring–Optional source type. Defaults to codex-generated for images under <CODEX_HOME>/generated_images (normally the user's .codex/generated_images), and to mcp-agent (an image saved by an AI assistant, sh…
stylestring––
tagsarray–Tags saved with the asset; searchable.
themestring––
user_promptstring–Optional user request kept separately from the effective generation prompt.
version_changestring––

No output schema declared.

No examples provided.

asset_duplicate ~41

Create an independent editable copy that starts a new version root while retaining duplicate provenance.

NameTypeReqDescription
assetIdstringyes–
assetIdNewstring––

No output schema declared.

No examples provided.

asset_get ~45

Get one saved asset and its full prompt recipe. asset_list and asset_search return only compact summaries; call this for the full recipe and metadata.

NameTypeReqDescription
assetIdstringyes–

No output schema declared.

No examples provided.

asset_import_folder ~253

Import every image and video found in a local folder into the GravityPort library, applying the same prompt/sourceType/source to each file. The folder path must be an absolute path on this machine. Symbolic links are skipped; with recursive: true the folder itself is level 1 and its contents are read down to level 5 (at most four subfolder levels below it), and deeper subfolders are skipped; a single call imports at most 1000 files, otherwise it fails and asks for batches. Identical bytes already in the library are reported as deduplicated. Files import one by one; a failed file is reported and does not stop the rest. Files already in the library are listed in duplicates with the existing assetId.

NameTypeReqDescription
folderPathstringyesAbsolute path of the folder to import.
promptstring––
recursiveboolean–Also read subfolders (default false; the folder itself is level 1, contents are read down to level 5, deeper subfolders are skipped).
sourceobject–Optional generation provenance applied to every imported file, such as generation_tool, model, or codex_session_id.
sourceTypestring––

No output schema declared.

No examples provided.

asset_list ~86

List saved GravityPort assets for a project, optionally filtered by search text. Returns compact per-asset summaries with the total count (20 per page by default, at most 100; pass `cursor` to page further); use asset_get for an asset's full recipe and metadata.

NameTypeReqDescription
cursorstring––
limitinteger––
querystring––

No output schema declared.

No examples provided.

asset_provenance_export ~137

Export a portable GravityPort provenance bundle plus an unsigned C2PA assertion payload. Prompts and user messages are excluded by default; pass includePrompts: true only when the user explicitly asks to include prompts. Local filesystem paths and usernames are never exported under any circumstances. This does not create a signed Content Credential; a C2PA signer must bind and sign the assertion separately.

NameTypeReqDescription
assetIdstringyes–
includePromptsboolean–Whether to include prompts and user messages. Defaults to false; pass true only when the user explicitly requests prompts. Local filesystem paths and usernames are never exported under any circumstan…

No output schema declared.

No examples provided.

asset_recipe_history ~32

Read immutable generation recipe snapshots for one asset and identify the currently active snapshot.

NameTypeReqDescription
assetIdstringyes–

No output schema declared.

No examples provided.

asset_restore ~27

Restore an asset from Trash back to the active library.

NameTypeReqDescription
assetIdstringyes–

No output schema declared.

No examples provided.

asset_search ~264

Search GravityPort visual memory using lexical search and explicit creation-time bounds. Multiple query words are combined with AND: every word must appear for an asset to match; OR is not supported. Returns compact per-asset summaries with the total match count (20 per page by default, at most 100; pass `cursor` to page further); use asset_get for an asset's full recipe and metadata.

NameTypeReqDescription
createdAfterstring–Inclusive lower creation-time bound. A date-only value ("2026-11-07") means local midnight of that day on this machine; a value with Z or a ±hh:mm offset keeps its explicit zone.
createdBeforestring–Inclusive upper creation-time bound. A date-only value ("2026-11-07") means local midnight of that day, so the bound is "before Nov 7 starts" — assets created on Nov 7 itself are outside. A value wit…
cursorstring––
limitinteger––
minScorenumber–Deprecated and ignored.
querystring–Space-separated words; every word must appear (AND). OR is not supported.
visualboolean–Deprecated and ignored.

No output schema declared.

No examples provided.

asset_trash ~107

Move an asset to Trash. Trashed assets can be restored with asset_restore or inside the GravityPort app, and are permanently purged after 90 days. Use this when the user asks to delete or remove an asset. Do NOT use this when the user asks to archive or stash an asset. If the user is viewing this asset in GravityPort, GravityPort asks the user first and the call waits up to 60 seconds for the answer.

NameTypeReqDescription
assetIdstringyes–

No output schema declared.

No examples provided.

asset_update_metadata ~218

Update metadata fields for a saved asset. Pass `references` to record reference rights and permitted uses for a saved asset; that annotation is not a generation input, so it appends a new recipe snapshot.

NameTypeReqDescription
assetIdstringyes–
business_fieldsobject–Stored with the asset but not searchable; put anything that should be findable via search into tags instead. Only the keys you pass are merged into the stored object: a key whose value is null is rem…
categorystring––
favoriteboolean––
groupstring––
negative_promptstring––
promptstring––
ratinginteger––
ratiostring––
recipe_change_summarystring––
referencesarray––
skillstring––
stylestring––
tagsarray––
themestring––
user_promptstring––

No output schema declared.

No examples provided.

asset_version_create ~281

Save a new recipe version as a child of an existing asset without overwriting the parent.

NameTypeReqDescription
assetIdstringyesExisting parent asset ID.
assetIdNewstring–Optional ID for the new version.
business_fieldsobject–Stored with the asset but not searchable; put anything that should be findable via search into tags instead.
categorystring––
favoriteboolean––
groupstring––
imagePathstring–Optional new image path; must be an absolute path on this machine (any local folder is accepted, same as asset_create). When omitted, the parent image is copied for a recipe-only version.
negative_promptstring––
promptstring––
ratinginteger––
ratiostring––
referencesarray––
skillstring––
sourceobject–Optional provenance for a replacement image, such as generation_tool, model, or codex_session_id.
sourceTypestring––
stylestring––
tagsarray––
themestring––
user_promptstring–Optional user request kept separately from the effective generation prompt.
version_changestringyesRequired summary of what changed from the parent.

No output schema declared.

No examples provided.

asset_version_history ~35

Read the complete root-to-descendant recipe version tree for an asset, including archived versions.

NameTypeReqDescription
assetIdstringyes–

No output schema declared.

No examples provided.

generation_lineage ~38

Read the connected generation lineage graph around one generation event, including parent/child IDs and evidence-bearing relations.

NameTypeReqDescription
generationIdstringyes–

No output schema declared.

No examples provided.

generation_list ~58

List generation occurrences, optionally filtered by output asset or provider identifiers.

NameTypeReqDescription
assetIdstring––
captureContextIdstring––
providerGenerationCallIdstring––
providerToolCallIdstring––

No output schema declared.

No examples provided.

generation_record ~266

Record one generation occurrence independently from the deduplicated output asset. Use this when an agent knows that a specific generation produced a saved GravityPort asset.

NameTypeReqDescription
batchIdstring––
captureChannelstring––
captureContextIdstring–GravityPort/local observation context. This is not a provider generation-call ID. Several generations in one capture context are told apart by providerToolCallId.
conversationIdstring––
createdAtstring––
effectivePromptstring––
evidenceobject––
messageIdstring––
modelstring––
outputAssetIdstringyesExisting GravityPort asset produced by this generation.
promptStatusstring––
providerstring––
providerAssetIdstring––
providerGenerationCallIdstring–Provider generation-call identifier only when actually supplied by the provider integration.
providerResponseIdstring––
providerToolCallIdstring–Provider/runtime tool-call identifier when observed.
referencesarray––
userPromptstring––
verificationLevel––Evidence level for this externally supplied record. provider_verified is reserved for trusted GravityPort provider integrations.

No output schema declared.

No examples provided.

generation_relation_record ~152

Record an explicit generation-to-generation relationship such as edited_from or variant_of. Do not infer a parent unless the evidence supports it. When verificationLevel is omitted the relation is recorded as user_confirmed (you are asserting it on the user's behalf); pass "observed" or "inferred" to record a weaker evidence level.

NameTypeReqDescription
childGenerationIdstringyes–
createdAtstring––
evidenceobject––
parentGenerationIdstringyes–
relationType––How the child relates to the parent; defaults to derived_from when omitted.
verificationLevel––Evidence level for this externally supplied record. provider_verified is reserved for trusted GravityPort provider integrations.

No output schema declared.

No examples provided.

stack_add_assets ~73

Add saved assets to an existing stack, after its current members. Assets already in this stack are skipped and listed in alreadyInStack. If any asset belongs to a different stack the call fails with ASSET_ALREADY_STACKED and nothing changes.

NameTypeReqDescription
assetIdsarrayyes–
stackIdstringyes–

No output schema declared.

No examples provided.

stack_create ~145

Group two or more saved assets into a new stack, the same as stacking a selection in the GravityPort app. coverAssetId defaults to the first asset. name (optional, at most 80 characters) is the stack's display name. An asset can belong to only one stack: if any asset is already in a stack the call fails with ASSET_ALREADY_STACKED and nothing changes; take it out with stack_remove_assets first. To show the same image in several stacks, copy it with asset_duplicate and stack the copy. Archived assets cannot be stacked.

NameTypeReqDescription
assetIdsarrayyes–
coverAssetIdstring––
namestring––

No output schema declared.

No examples provided.

stack_dissolve ~46

Dissolve a stack: its assets return to the library as separate assets; nothing is deleted or archived. They are not stacked again automatically.

NameTypeReqDescription
stackIdstringyes–

No output schema declared.

No examples provided.

stack_get ~45

Read one stack: its name, cover, member count, and member asset IDs in stack order. Members in Trash or archived are left out.

NameTypeReqDescription
stackIdstringyes–

No output schema declared.

No examples provided.

stack_list ~52

List the stacks shown in the GravityPort library (two or more visible members), most recently updated first, optionally filtered by text in the stack name.

NameTypeReqDescription
limitinteger––
querystring––

No output schema declared.

No examples provided.

stack_remove_assets ~86

Take assets out of a stack; the assets stay in the library. Every assetId must belong to this stack, otherwise the call fails with ASSET_NOT_IN_STACK and nothing changes. A stack left with one asset is dissolved (dissolved: true). Assets taken out are not stacked again automatically.

NameTypeReqDescription
assetIdsarrayyes–
stackIdstringyes–

No output schema declared.

No examples provided.

stack_rename ~56

Set a stack's display name (trimmed, 1 to 80 characters). The name is kept even when the stack was created automatically from a conversation.

NameTypeReqDescription
namestringyes–
stackIdstringyes–

No output schema declared.

No examples provided.

Install

How do I install the GravityPort MCP server?

GravityPort runs locally as an npm package, launched with npx -y gravityport-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 · gravityport-mcp

# add to Claude Code
claude mcp add fengseekling-coder-gravityport -- npx -y gravityport-mcp
Common questions

What is the GravityPort MCP server?

GravityPort is an MCP server listed in the public MCP registry as io.github.fengseekling-coder/gravityport. Built into the GravityPort desktop app: install it, then Claude or Codex can search your AI library. This page covers its npm package (gravityport-mcp).

Is the GravityPort MCP server safe to use?

GravityPort scores 64 out of 100 on VerifyMCP. We found no known CVEs affecting 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 GravityPort MCP server expose?

GravityPort exposes 25 tools: asset_create, asset_import_folder, asset_list, asset_search, asset_get, and 20 more. Their descriptions and schemas cost roughly 2,969 tokens of context every time the server is loaded.

Is the GravityPort MCP server still maintained?

GravityPort 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 GravityPort MCP server under?

GravityPort declares the PolyForm-Shield-1.0.0 licence, which is not on the OSI-approved list. Read the terms before using it at work, and note this covers the source only, not the cost of any service it calls.

What did VerifyMCP test on the GravityPort MCP server?

VerifyMCP ran 15 checks on GravityPort, 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 GravityPort: Stability. One category scores 0 for that reason, because we only credit what we can confirm. 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.