Agent skill

Lifi MCP Skill

by holon-run in holon-run/uxc

Use the LI.FI MCP server through UXC for cross-chain route discovery, bridge/DEX availability checks, token and chain lookup, gas/balance/allowance checks, quote generation, and transfer status…

MITAuto-check passedAgent Workflows

Install Lifi MCP Skill

skills CLI
$ npx skills add holon-run/uxc --skill lifi-mcp-skill -a claude-code

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

GitHub CLI
$ gh skill install holon-run/uxc lifi-mcp-skill --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/holon-run/uxc.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/lifi-mcp-skill .claude/skills/lifi-mcp-skill && 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
lifi-mcp-skill
GitHub stars
116
Token cost
~1.2k tokens
SKILL.md length
513 words
Files
4 (incl. scripts, references)
Skills in repo
62
Repo updated
First seen
Licence
MIT

At a glance

Use the LI.FI MCP server through UXC for cross-chain route discovery, bridge/DEX availability checks, token and chain lookup, gas/balance/allowance checks, quote generation, and transfer status…

  • Works in 5 steps: Verify endpoint and protocol with… → Optional auth setup for higher rate limits → Use a fixed link command by default → …
  • Tasks involve planning
  • SKILL.md covers Prerequisites, Core Workflow, Capability Map and Recommended Usage Pattern, plus 3 more sections
  • Runs Shell scripts from its folder; reaches mcp.li.quest; needs LIFI_API_KEY

What it does

Lifi MCP Skill is an agent skill from holon-run/uxc. Use the LI.FI MCP server through UXC for cross-chain route discovery, bridge/DEX availability checks, token and chain lookup, gas/balance/allowance checks, quote generation, and transfer status tracking. Use when tasks involve planning or monitoring cross-chain swaps and bridges without signing or broadcasting transactions.

Its SKILL.md is about 1.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 6 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/usage-patterns.md` and `scripts/validate.sh`).

It sits in Agent Workflows, covering MCP servers and Project management. It works with Model Context Protocol. The repository describes itself as: A unified CLI for discovering and invoking tools across OpenAPI, MCP, GraphQL, gRPC, and JSON-RPC. The licence is MIT.

When your agent uses it

  • Tasks involve planning
  • Monitoring cross-chain swaps and bridges without signing
  • Broadcasting transactions

Example prompts

  • “/lifi-mcp-skill”

Requirements

  • A Bash shell
  • A credential in LIFI_API_KEY

Workflow steps

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

  1. Verify endpoint and protocol with help-first probing
  2. Optional auth setup for higher rate limits
  3. Use a fixed link command by default
  4. Inspect operation schema before execution
  5. Prefer discovery first, then route/quote, then execution-precheck queries.

What it can do on your machine

Read from SKILL.md and the folder at commit 562d47c. 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.

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • mcp.li.quest

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

  • Credentials

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

    • LIFI_API_KEY

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

Context cost

Lifi MCP Skill loads about 1.2k tokens when it runs, and up to ~2k if it reads all its reference files. Until then it costs about 85 tokens; SKILL.md has 513 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
~1.2k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~2k

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 passed

The automated check found no risky patterns in SKILL.md.

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 holon-run/uxc at commit 562d47c, republished under its MIT licence (© holon-run). 513 words, ~1,234 tokens.

Download SKILL.mdSave it as .claude/skills/lifi-mcp-skill/SKILL.md (or your agent's skills folder). This skill also uses 3 other files; get the full folder from GitHub.
name
lifi-mcp-skill
description
Use the LI.FI MCP server through UXC for cross-chain route discovery, bridge/DEX availability checks, token and chain lookup, gas/balance/allowance checks, quote generation, and transfer status tracking. Use when tasks involve planning or monitoring cross-chain swaps and bridges without signing or broadcasting transactions.

LI.FI MCP Skill

Use this skill to run LI.FI MCP operations through uxc.

Reuse the uxc skill for generic protocol discovery, auth binding, envelope parsing, and error handling.

Prerequisites

  • uxc is installed and available in PATH.
  • Network access to https://mcp.li.quest/mcp.
  • Optional: a LI.FI API key for higher rate limits.

Core Workflow

  1. Verify endpoint and protocol with help-first probing:
    • uxc https://mcp.li.quest/mcp -h
    • Confirm protocol is MCP (protocol == "mcp" in the envelope).
  2. Optional auth setup for higher rate limits:
    • uxc auth credential set lifi-mcp --auth-type bearer --secret-env LIFI_API_KEY
    • uxc auth binding add --id lifi-mcp --host mcp.li.quest --path-prefix /mcp --scheme https --credential lifi-mcp --priority 100
    • LI.FI accepts either Authorization: Bearer <key> or X-LiFi-Api-Key; prefer bearer unless endpoint behavior changes.
  3. Use a fixed link command by default:
    • command -v lifi-mcp-cli
    • If missing, create it:
      • uxc link lifi-mcp-cli https://mcp.li.quest/mcp
    • lifi-mcp-cli -h
  4. Inspect operation schema before execution:
    • lifi-mcp-cli get-chains -h
    • lifi-mcp-cli get-token -h
    • lifi-mcp-cli get-quote -h
    • lifi-mcp-cli get-status -h
  5. Prefer discovery first, then route/quote, then execution-precheck queries.

Capability Map

  • Chain and token discovery:
    • get-chains
    • get-chain-by-id
    • get-chain-by-name
    • get-tokens
    • get-token
  • Route discovery and provider availability:
    • get-connections
    • get-tools
  • Quotes and route planning:
    • get-quote
    • get-routes
    • get-step-transaction
    • get-quote-with-calls
  • Wallet prechecks:
    • get-native-token-balance
    • get-token-balance
    • get-allowance
    • get-gas-prices
    • get-gas-suggestion
  • Monitoring and service checks:
    • get-status
    • test-api-key
    • health-check

Always inspect host help and operation help in the current endpoint version before relying on an operation name or argument shape.

  1. Discover chain IDs dynamically:
    • lifi-mcp-cli get-chains
    • lifi-mcp-cli get-chain-by-name name=base
  2. Resolve token addresses before quoting:
    • lifi-mcp-cli get-token chain=8453 token=USDC
  3. Check whether a route exists before asking for a quote:
    • lifi-mcp-cli get-connections fromChain=8453 toChain=42161
  4. Generate the quote:
    • lifi-mcp-cli get-quote fromChain=8453 toChain=42161 fromToken=USDC toToken=USDC fromAddress=<wallet> fromAmount=<smallest-unit-amount>
  5. Validate execution preconditions:
    • lifi-mcp-cli get-allowance ...
    • lifi-mcp-cli get-native-token-balance ...
  6. Use get-status only after the externally signed transaction has been broadcast.
Show full SKILL.md (216 more words)Show less

Guardrails

  • Keep automation on JSON output envelope; do not rely on --text.
  • Parse stable fields first: ok, kind, protocol, data, error.
  • Use lifi-mcp-cli as the default command path.
  • lifi-mcp-cli <operation> ... is equivalent to uxc https://mcp.li.quest/mcp <operation> ... when the same auth binding is configured.
  • Use direct uxc "<endpoint>" ... only as a temporary fallback when link setup is unavailable.
  • Prefer key=value for simple arguments and positional JSON for nested objects.
  • This endpoint is read-only from the agent perspective:
    • it does not sign transactions
    • it does not broadcast transactions
    • it returns unsigned transactionRequest objects for external wallet execution
  • Do not present get-quote or get-step-transaction as executed trades; they are execution plans only.
  • Before suggesting an ERC20 route as ready to execute, check allowance if the route needs approval.
  • Prefer get-routes only when the user explicitly wants multiple alternatives; default to get-quote for the best route.
  • In live testing, chain lookup tools accepted names, but token/balance/allowance tools were more reliable with numeric chain IDs. Prefer numeric IDs after discovery.

Tested Real Scenario

The endpoint was verified through uxc host discovery and returned a live MCP tool list including:

  • get-allowance
  • get-chain-by-id
  • get-chain-by-name
  • get-chains
  • get-connections
  • get-gas-prices
  • get-gas-suggestion
  • get-quote
  • get-routes
  • get-status
  • get-token
  • get-tokens
  • get-tools
  • health-check

This confirms the skill target is a real hosted MCP surface accessible via UXC.

References

  • Invocation patterns:
    • references/usage-patterns.md

© holon-run, MIT. 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 3 other files (scripts, references) in skills/lifi-mcp-skill of holon-run/uxc.

  • SKILL.md
  • agents/openai.yaml
  • references/usage-patterns.md
  • scripts/validate.sh

Open the folder on GitHubat commit 562d47c

Compare with similar skills

Lifi MCP Skill 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.

Lifi MCP Skill compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Lifi MCP Skill this skillholon-run/uxc116—~1.2kAutomated safety check: PassMIT
Mps Project ManagementJetBrains/MPS1.7k—~2.2kAutomated safety check: PassApache-2.0
State Memory MCPputervision/state-memory-mcp50—~1.9kAutomated safety check: PassMIT
Patsnap Drug Assetpatsnap/mcp113—~653Automated safety check: PassApache-2.0
Jira Natural Language Interfacejjmartres/opencode1333 repos~1.7kAutomated safety check: PassMIT
LinearAlexAI-MCP/hermes-CCC135—~916Automated safety check: PassMIT

Similar skills

  • Official

    Open an MPS project in a running or freshly started MPS instance when MCP tools fail because no project is open (welcome screen), close an open project with mpsmcpcloseproject, or create a new empty…

    1.7k GitHub stars~2.2k tokensUpdated yesterday
    Agent WorkflowsAuto-check passed
  • State Memory MCP

    putervision/state-memory-mcp

    Teaches the agent to use the state-memory-mcp MCP server to track workflow state, tasks, decisions, blockers, artifacts, plans, milestones, and their semantic relationships in a persistent graph…

    50 GitHub stars~1.9k tokensUpdated 7 days ago
    Agent WorkflowsAuto-check passed
  • Patsnap Drug & Asset MCP for AI agents. An agent skill from patsnap/mcp.

    113 GitHub stars~653 tokensUpdated 1 mo ago
    Agent WorkflowsAuto-check passed
  • Lets an agent view, create, update and transition Jira issues in natural language, automatically choosing between the jira CLI and Atlassian MCP tools.

    133 GitHub starsUsed in 3 repos~1.7k tokens
    Product & Project ManagementAuto-check passed
  • Linear

    AlexAI-MCP/hermes-CCC

    Linear project management — create issues, manage cycles, update projects, and query team progress via Linear API or MCP.

    135 GitHub stars~916 tokensUpdated 6 mo ago
    Backend & APIsAuto-check passed
  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed

More from holon-run/uxc

All 62 skills in this repo
  • Context7 MCP Skill

    holon-run/uxc

    Query up-to-date library documentation and code examples using Context7 MCP.

    116 GitHub stars~564 tokensUpdated 26 days ago
    Auto-check passed
  • Deepwiki MCP Skill

    holon-run/uxc

    Ask questions and read documentation about any GitHub repository using DeepWiki MCP.

    116 GitHub stars~700 tokensUpdated 26 days ago
    Auto-check passed
  • Operate Linear workspace issues, projects, and teams through Linear GraphQL API using UXC.

    116 GitHub stars~1.8k tokensUpdated 26 days ago
    Auto-check passed
  • Operate Notion Public API through UXC with a curated OpenAPI schema for search, block traversal, page reads, content writes, and data source/database inspection.

    116 GitHub stars~2.3k tokensUpdated 26 days ago
    Auto-check passed
  • Operate Alchemy Prices API reads through UXC with a curated OpenAPI schema, path-templated API-key auth, and read-first guardrails.

    116 GitHub starsUsed in 1 repo~1k tokens
    Auto-check passed
  • Uxc

    holon-run/uxc

    Discover and call remote schema-exposed interfaces with UXC.

    116 GitHub stars~1.8k tokensUpdated 26 days ago
    Auto-check passed

Questions about Lifi MCP Skill

What does Lifi MCP Skill do?

Use the LI.FI MCP server through UXC for cross-chain route discovery, bridge/DEX availability checks, token and chain lookup, gas/balance/allowance checks, quote generation, and transfer status…. Lifi MCP Skill is an agent skill from holon-run/uxc.FI MCP server through UXC for cross-chain route discovery, bridge/DEX availability checks, token and chain lookup, gas/balance/allowance checks, quote generation, and transfer status tracking.

When should I use Lifi MCP Skill?

Lifi MCP Skill fits situations like: tasks involve planning; monitoring cross-chain swaps and bridges without signing; broadcasting transactions.

How do I install Lifi MCP Skill in Claude Code?

Run `npx skills add holon-run/uxc --skill lifi-mcp-skill -a claude-code`. Or copy the skill folder (skills/lifi-mcp-skill in holon-run/uxc) into .claude/skills/lifi-mcp-skill in your project. Claude Code loads it when a task matches its description.

How do I install Lifi MCP Skill in Codex?

Run `npx skills add holon-run/uxc --skill lifi-mcp-skill -a codex`. Or copy the skill folder (skills/lifi-mcp-skill in holon-run/uxc) into .agents/skills/lifi-mcp-skill in your project. Codex loads it when a task matches its description.

Can I use Lifi MCP Skill 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 holon-run/uxc --skill lifi-mcp-skill -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/lifi-mcp-skill, .gemini/skills/lifi-mcp-skill, .github/skills/lifi-mcp-skill and .opencode/skills/lifi-mcp-skill in your project.

What does Lifi MCP Skill need to run?

Going by SKILL.md and its folder, Lifi MCP Skill needs a shell for the scripts in its folder and credentials named LIFI_API_KEY. Our summary lists: A Bash shell; A credential in LIFI_API_KEY.

Does Lifi MCP Skill access the network?

SKILL.md names 1 domain. In commands or code: mcp.li.quest; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Lifi MCP Skill safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. 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 Lifi MCP Skill use?

Lifi MCP Skill is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Lifi MCP Skill use?

About 1.2k tokens (SKILL.md is roughly 4.9k 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 722 tokens, read only when the agent opens those files.

What are the alternatives to Lifi MCP Skill?

Skills that share tags, products or a category with Lifi MCP Skill: Mps Project Management (JetBrains/MPS, 1.7k stars), State Memory MCP (putervision/state-memory-mcp, 50 stars), Patsnap Drug Asset (patsnap/mcp, 113 stars) and Jira Natural Language Interface (jjmartres/opencode, 133 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Lifi MCP Skill?

holon-run (a GitHub organization) maintains it in holon-run/uxc, which has 116 GitHub stars. The repository holds 62 skills in this directory. The repository was last updated on September 15, 2026.

Source: holon-run/uxc on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.