Agent skill

Vss MCP Integration

by open-edge-platform in open-edge-platform/edge-ai-libraries

Helps developers configure and extend the Video Search and Summarization sample app's spec-driven FastMCP proxy for VSS search.

Apache-2.0Auto-check: notesAgent Workflows

Install Vss MCP Integration

skills CLI
$ npx skills add open-edge-platform/edge-ai-libraries --skill vss-mcp-integration -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install open-edge-platform/edge-ai-libraries vss-mcp-integration --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/open-edge-platform/edge-ai-libraries.git skills-src && mkdir -p .claude/skills && cp -r skills-src/sample-applications/video-search-and-summarization/.github/skills/vss-mcp-integration .claude/skills/vss-mcp-integration && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
vss-mcp-integration
GitHub stars
169
Token cost
~1.5k tokens
SKILL.md length
568 words
Files
14 (incl. scripts, references)
Skills in repo
29
Repo updated
First seen
Licence
Apache-2.0

At a glance

Helps developers configure and extend the Video Search and Summarization sample app's spec-driven FastMCP proxy for VSS search.

  • Works in 5 steps: reads env into Settings; → loads FILTER_FILE_PATH with… → fetches the live VSS OpenAPI/Swagger… → …
  • The user wants to connect an AI agent to VSS search
  • SKILL.md covers Environment setup (run first), Ground truth files, How the proxy works and Run and connect, plus 3 more sections
  • Runs Shell scripts from its folder; calls bash, docker and poetry; needs MCP_PROXY_AUTH_TOKEN

What it does

Vss MCP Integration is an agent skill from open-edge-platform/edge-ai-libraries. Helps developers configure and extend the Video Search and Summarization sample app's spec-driven FastMCP proxy for VSS search. Use when the user wants to connect an AI agent to VSS search, add an MCP tool to VSS, configure the VSS MCP server / filters, run the FastMCP proxy, or debug why isn't my MCP tool showing up.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 17 other files, including scripts and reference files (for example `BENCHMARK.md`, `evals/evals.json` and `evals/trigger-evals.json`).

It sits in Agent Workflows, covering MCP servers and Summarization. It works with Model Context Protocol and OpenAPI. The repository describes itself as: Libraries, microservices, tools, and other reference software, supporting development of performance-optimized Edge AI applications. The licence is Apache-2.0.

When your agent uses it

  • The user wants to connect an AI agent to VSS search
  • Add an MCP tool to VSS
  • Configure the VSS MCP server / filters
  • Run the FastMCP proxy

Example prompts

  • “Use the vss-mcp-integration skill to help developers configure and extend the Video Search and Summarization sample app's spec-driven FastMCP proxy…”
  • “/vss-mcp-integration”

Requirements

  • A Bash shell
  • Docker
  • A credential in MCP_PROXY_AUTH_TOKEN

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. reads env into Settings;
  2. loads FILTER_FILE_PATH with load_filter_config();
  3. fetches the live VSS OpenAPI/Swagger JSON from API_SPEC_URL;
  4. creates an httpx.AsyncClient(base_url=API_BASE_URL);
  5. calls FastMCP.from_openapi(...) with

What it can do on your machine

Read from SKILL.md and the folder at commit cdf860c. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • bash
    • docker
    • poetry

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use docker, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • MCP_PROXY_AUTH_TOKEN

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Vss MCP Integration loads about 1.5k tokens when it runs, and up to ~4.3k if it reads all its reference files. Until then it costs about 85 tokens; SKILL.md has 568 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~85
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:61
    cp .env.example .env

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from open-edge-platform/edge-ai-libraries at commit cdf860c, republished under its Apache-2.0 licence (© open-edge-platform). 568 words, ~1,506 tokens.

Download SKILL.mdSave it as .claude/skills/vss-mcp-integration/SKILL.md (or your agent's skills folder). This skill also uses 13 other files; get the full folder from GitHub.
name
vss-mcp-integration
description
Helps developers configure and extend the Video Search and Summarization sample app's spec-driven FastMCP proxy for VSS search. Use when the user wants to connect an AI agent to VSS search, add an MCP tool to VSS, configure the VSS MCP server / filters, run the FastMCP proxy, or debug why isn't my MCP tool showing up.

VSS MCP Integration

Use this for sample-applications/video-search-and-summarization/mcp: the Search-mode MCP server that proxies selected VSS REST endpoints to agents via FastMCP.

Environment setup (run first)

This skill drives the Video Search & Summarization app through its real source files, so the VSS application must be present and you must run commands from its app root. Do this before anything else, and it works whether or not the VSS source is already in your workspace.

Run the bundled bootstrap. It first tries to find an existing VSS checkout - walking up from the current directory and inspecting the enclosing git repo - and reuses it without ever re-cloning. Only when no checkout is found does it do a shallow, single-branch, sparse checkout of just sample-applications/video-search-and-summarization from main. It prints the resolved app root on stdout:

bash
# SKILL_DIR is THIS skill's own directory (shown to you when the skill loads);
# in-repo it is .github/skills/vss-mcp-integration. Works the same if the skill is installed standalone.
SKILL_DIR=".github/skills/vss-mcp-integration"
APP_ROOT="$(bash "$SKILL_DIR/scripts/vss-bootstrap.sh")"
cd "$APP_ROOT"

Every command below assumes the working directory is this APP_ROOT. To pull from a fork/branch or reuse a specific checkout dir, override VSS_REPO_URL, VSS_REPO_BRANCH, or VSS_CLONE_DIR before running it.

Ground truth files

Read these before changing behavior: mcp/src/server.py, mcp/src/core/config.py, mcp/src/filters/config.py, mcp/src/openapi/{loader.py,mapping.py}, mcp/search.json, mcp/compose.yaml, mcp/.env.example, mcp/README.md, docs/user-guide/mcp-server.md, and mcp/tests/*.

How the proxy works

Startup path: src.main:main calls get_settings(), get_mcp(), then server.run(transport="streamable-http", host=MCP_HOST, port=MCP_PORT, path=MCP_PATH, stateless_http=MCP_STATELESS_HTTP).

create_mcp() in mcp/src/server.py:

  1. reads env into Settings;
  2. loads FILTER_FILE_PATH with load_filter_config();
  3. fetches the live VSS OpenAPI/Swagger JSON from API_SPEC_URL;
  4. creates an httpx.AsyncClient(base_url=API_BASE_URL);
  5. calls FastMCP.from_openapi(...) with:
    • mcp_names=build_mcp_names(spec, filter_config)
    • route_map_fn=build_route_map_fn(filter_config)
    • mcp_component_fn=build_component_fn(filter_config)

The filter is allow-list based. Operations not listed in apis are mapped to MCPType.EXCLUDE. This spec-driven design is why a path/method mismatch can look like a missing tool: the OpenAPI route is simply excluded rather than treated as an error.

Run and connect

From mcp/:

bash
cp .env.example .env
docker compose up --build -d

Edit VSS_IP and HOST_IP first. Defaults: MCP server http://<HOST_IP>:8000/mcp; Inspector http://<HOST_IP>:6274. In Inspector, choose Streamable HTTP and connect to the MCP URL.

For local Poetry runs, set all required env vars explicitly:

bash
cd sample-applications/video-search-and-summarization/mcp
API_SPEC_URL=http://<VSS_IP>:12345/manager/swagger/json \
API_BASE_URL=http://<VSS_IP>:12345/manager \
FILTER_FILE_PATH="$PWD/search.json" \
poetry run mcp-app

Real config keys

Required by mcp/src/core/config.py: API_SPEC_URL, API_BASE_URL, FILTER_FILE_PATH.

Optional: REQUEST_TIMEOUT default 60, LOG_LEVEL default INFO, MCP_HOST default 0.0.0.0, MCP_PORT default 8000, MCP_PATH default /mcp, MCP_STATELESS_HTTP default true.

Compose also uses VSS_IP, HOST_IP, INSPECTOR_CLIENT_PORT, DANGEROUSLY_OMIT_AUTH, MCP_PROXY_AUTH_TOKEN, and proxy vars.

Show full SKILL.md (223 more words)Show less

Add or filter a tool/resource

Edit mcp/search.json or point FILTER_FILE_PATH to another JSON file. Format:

json
{
  "server_name": "vss_search_mcp",
  "prefix": "vss",
  "apis": {
    "POST /search/query": {
      "type": "tool",
      "name": "run_search_query",
      "description": "Execute an immediate natural-language search."
    }
  }
}

Rules from mcp/src/filters/config.py:

  • API keys must be exact canonical "METHOD /path" entries matching the OpenAPI path, e.g. "GET /videos/{videoId}".
  • Supported methods: GET, PUT, POST, DELETE, PATCH, HEAD, OPTIONS; wildcards are rejected.
  • type is only "tool" or "resource"; resources must be GET.
  • name, prefix, and server_name must be valid identifiers; final names are {prefix}_{name}.
  • Duplicate name values are rejected across tools/resources.
  • Unknown fields such as old expose / tool_name are rejected.

Restart the MCP server after changing the filter; it reads the spec and filter at startup.

Debug missing tools

  1. Confirm the backend and spec URL work: API_SPEC_URL must return JSON with paths.
  2. Confirm FILTER_FILE_PATH exists inside the process/container. Compose mounts ./search.json to /app/search.json.
  3. Compare the filter key with the live spec exactly: method and path must match, including {param} names.
  4. Check the endpoint has an OpenAPI operationId; build_mcp_names() only renames filtered operations with operation IDs.
  5. Check filter validation: resource on non-GET, duplicate names, invalid identifiers, wildcards, or extra fields fail startup.
  6. Run with LOG_LEVEL=DEBUG to see [exclude], [tool], [resource], and rename logs from mcp/src/openapi/mapping.py.
  7. Remember POST /videos is intentionally not exposed in the user guide; uploads should use the REST API directly.

See references/mcp-spec-driven.md for the detailed spec/filter model and an example.

© open-edge-platform, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 13 other files (scripts, references) in sample-applications/video-search-and-summarization/.github/skills/vss-mcp-integration of open-edge-platform/edge-ai-libraries.

  • SKILL.md
  • BENCHMARK.md
  • evals/evals.json
  • evals/trigger-evals.json
  • example-prompts/01-start-and-connect-claude.md
  • example-prompts/02-add-endpoint-as-tool.md
  • example-prompts/03-custom-filter-compose-mount.md
  • example-prompts/04-debug-missing-tool.md
  • example-prompts/05-local-poetry-run.md
  • example-prompts/06-upload-endpoint-not-exposed.md
  • example-prompts/07-bootstrap-fresh-machine.md
  • example-prompts/README.md
  • references/mcp-spec-driven.md
  • scripts/vss-bootstrap.sh

Open the folder on GitHubat commit cdf860c

Compare with similar skills

Vss MCP Integration next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Vss MCP Integration compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Vss MCP Integration this skillopen-edge-platform/edge-ai-libraries169—~1.5kAutomated safety check: NotesApache-2.0
Generate MCP Servertrycompai/comp2k—~2.7kAutomated safety check: PassApache-2.0
MCP Server Builderalirezarezvani/claude-skills28k—~985Automated safety check: PassMIT
CLI MCP DocsChatbotXIO/ChatbotX881—~1.5kAutomated safety check: PassCustom licence
MCP Server Builderborghei/Claude-Skills886—~1.9kAutomated safety check: PassMIT
Kingdee MCP DevWaHaiLong/KingdeeMCP105—~853Automated safety check: PassMIT

Similar skills

  • Generate MCP Server

    trycompai/comp

    A skill your agent uses when generating an MCP server from an OpenAPI spec with Speakeasy.

    2k GitHub stars~2.7k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed
  • MCP Server Builder

    alirezarezvani/claude-skills

    Design and ship production-ready MCP (Model Context Protocol) servers from OpenAPI contracts instead of hand-written tool wrappers.

    28k GitHub stars~985 tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed
  • CLI MCP Docs

    ChatbotXIO/ChatbotX

    Use as the last step of every new feature or new operation (every one ships a public procedure — AGENTS.md invariant 23), and after adding, renaming, or removing a public oRPC procedure or changing…

    881 GitHub stars~1.5k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • MCP Server Builder

    borghei/Claude-Skills

    Build MCP (Model Context Protocol) servers with tool definitions, resource providers, prompt templates, and transports.

    886 GitHub stars~1.9k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed
  • Kingdee MCP Dev

    WaHaiLong/KingdeeMCP

    Knowledge base for the Kingdee MCP Dev Squad. An agent skill from WaHaiLong/KingdeeMCP.

    105 GitHub stars~853 tokensUpdated 1 mo ago
    Backend & APIsAuto-check passed
  • Sap Hana CLI

    secondsky/sap-skills

    Assists with SAP HANA Developer CLI (hana-cli) for database development and administration.

    462 GitHub stars~3.1k tokensUpdated 4 days ago
    DatabasesAuto-check: notes

More from open-edge-platform/edge-ai-libraries

All 29 skills in this repo
  • Time Series Analytics User

    open-edge-platform/edge-ai-libraries

    Build a new time-series analytics use case on top of the deployed Time Series Analytics microservice — bring it up with Docker Compose (from a repo clone, or by fetching the compose files from…

    169 GitHub stars~3.1k tokensUpdated today
    Auto-check passed
  • Vss Add Nest Module

    open-edge-platform/edge-ai-libraries

    Scaffolds and wires a new NestJS service/module for the Video Search & Summarization sample app's pipeline-manager using the repo's real conventions.

    169 GitHub stars~2.5k tokensUpdated today
    Auto-check passed
  • Chatqna Helm Deploy

    open-edge-platform/edge-ai-libraries

    Deploy Chat Question-and-Answer Core to Kubernetes using Helm (OpenVINO CPU, OpenVINO GPU, or Ollama), including values.yaml configuration, helm install/upgrade, deployment verification, uninstall…

    169 GitHub stars~2.3k tokensUpdated today
    Auto-check passed
  • Generate Changelog

    open-edge-platform/edge-ai-libraries

    Generates or updates CHANGELOG.md by analyzing git commit history between two branches, tags, or revisions in ANY git repository or folder.

    169 GitHub stars~3.1k tokensUpdated today
    Auto-check passed
  • Vss Deploy

    open-edge-platform/edge-ai-libraries

    Deploys and manages VSS through setup.sh and its Docker Compose overlays.

    169 GitHub stars~4.1k tokensUpdated today
    Auto-check passed
  • Vss Deploy Helm

    open-edge-platform/edge-ai-libraries

    A skill your agent uses whenever a developer needs to deploy VSS to Kubernetes, helm install VSS, configure values.yaml for VSS, or run VSS on k8s with GPU/vLLM for the…

    169 GitHub stars~3.8k tokensUpdated today
    Auto-check passed

Categories

Questions about Vss MCP Integration

What does Vss MCP Integration do?

Helps developers configure and extend the Video Search and Summarization sample app's spec-driven FastMCP proxy for VSS search. Vss MCP Integration is an agent skill from open-edge-platform/edge-ai-libraries. Helps developers configure and extend the Video Search and Summarization sample app's spec-driven FastMCP proxy for VSS search.

When should I use Vss MCP Integration?

Vss MCP Integration fits situations like: the user wants to connect an AI agent to VSS search; add an MCP tool to VSS; configure the VSS MCP server / filters; run the FastMCP proxy.

How do I install Vss MCP Integration in Claude Code?

Run `npx skills add open-edge-platform/edge-ai-libraries --skill vss-mcp-integration -a claude-code`. Or copy the skill folder (sample-applications/video-search-and-summarization/.github/skills/vss-mcp-integration in open-edge-platform/edge-ai-libraries) into .claude/skills/vss-mcp-integration in your project. Claude Code loads it when a task matches its description.

How do I install Vss MCP Integration in Codex?

Run `npx skills add open-edge-platform/edge-ai-libraries --skill vss-mcp-integration -a codex`. Or copy the skill folder (sample-applications/video-search-and-summarization/.github/skills/vss-mcp-integration in open-edge-platform/edge-ai-libraries) into .agents/skills/vss-mcp-integration in your project. Codex loads it when a task matches its description.

Can I use Vss MCP Integration in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add open-edge-platform/edge-ai-libraries --skill vss-mcp-integration -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/vss-mcp-integration, .gemini/skills/vss-mcp-integration, .github/skills/vss-mcp-integration and .opencode/skills/vss-mcp-integration in your project.

What does Vss MCP Integration need to run?

Going by SKILL.md and its folder, Vss MCP Integration needs a shell for the scripts in its folder, the command-line tools its instructions call (bash, docker and poetry) and credentials named MCP_PROXY_AUTH_TOKEN. Our summary lists: A Bash shell; Docker; A credential in MCP_PROXY_AUTH_TOKEN.

Does Vss MCP Integration access the network?

SKILL.md contains no URLs. Its commands use docker, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Vss MCP Integration safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Vss MCP Integration use?

Vss MCP Integration is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Vss MCP Integration use?

About 1.5k tokens (SKILL.md is roughly 6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.8k tokens, read only when the agent opens those files.

What are the alternatives to Vss MCP Integration?

Skills that share tags, products or a category with Vss MCP Integration: Generate MCP Server (trycompai/comp, 2k stars), MCP Server Builder (alirezarezvani/claude-skills, 28k stars), CLI MCP Docs (ChatbotXIO/ChatbotX, 881 stars) and MCP Server Builder (borghei/Claude-Skills, 886 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Vss MCP Integration?

open-edge-platform (a GitHub organization) maintains it in open-edge-platform/edge-ai-libraries, which has 169 GitHub stars. The repository holds 29 skills in this directory. The repository was last updated on October 9, 2026.

Source: open-edge-platform/edge-ai-libraries on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.