rylsherdamz-rgbrylsherdamz-rgb/stellar-forge/skills/stellar-mcp/SKILL.md

stellar-mcp

Skill17 starsChanged 2 months agoMITView on GitHub

MCP (Model Context Protocol) tools for Stellar development. Gives Claude direct access to the Stellar blockchain, filesystem, GitHub, and Playwright through configured MCP servers. Use when querying chain data, deploying contracts, managing repos, or running e2e tests from within the agent.

In this repository32 other files it gives its agents.
- references/agents.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- banner-designSkill
- brandkitSkill
- brandSkill
- designSkill
- design-systemSkill
- design-taste-frontendSkill
- design-taste-frontend-v1Skill
- full-output-enforcementSkill
- gpt-tasteSkill
- high-end-visual-designSkill
- imagegen-frontend-mobileSkill
- imagegen-frontend-webSkill
- image-to-codeSkill
- industrial-brutalist-uiSkill
- minimalist-uiSkill
- redesign-existing-projectsSkill
- slidesSkill
- stitch-design-tasteSkill
- ui-stylingSkill
- ui-ux-pro-maxSkill
- stellar-forgeSkill
- agentic-paymentsSkill
- assetsSkill
- dappSkill
- dataSkill
- frontend-designSkill
- graphifySkill
- smart-contractsSkill
- standardsSkill
- zk-proofsSkill

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific
could be automatic: a setting could enforce it

Distinctive:
Read and write project files directly.
line 48
Distinctive:
Run browser-based e2e tests for Stellar dApps.
line 72
Distinctive:
Use MCP tools during development and debugging only
line 96
Very specific:
Never commit secrets to .mcp.json — use env field with user-provided values
line 98
Very specific:
Use stellar-rpc for quick checks.
line 99

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

Stellar MCP Tools

Claude has direct access to the Stellar blockchain, filesystem, and GitHub through MCP servers configured in .mcp.json.

Available MCP Servers

`stellar-rpc`

Direct blockchain queries without leaving the conversation.

Tools available:
- get_account(address)       → account balance, sequence, signers
- get_contract_data(id, key)  → contract storage entry
- simulate_transaction(xdr)   → simulate before submitting
- send_transaction(xdr)       → submit signed transaction
- get_events(contractId)      → query contract events
- get_ledger_entries(keys)    → raw ledger entries

Use for:

Checking account balances during development
Verifying contract state after deployment
Debugging transaction failures with simulation
Querying contract events without writing frontend code

`filesystem`

Read and write project files directly.

Tools available:
- read_file(path)     → read file contents
- write_file(path)    → write file contents
- list_directory(path) → list files in directory
- search_files(pattern) → search by glob
- get_file_info(path)  → file metadata

`github`

Manage repositories, PRs, issues, and code search.

Tools available:
- create_or_update_file  → commit changes
- search_repositories    → find repos
- get_issue             → read issue details
- create_pull_request   → open PRs
- list_issues           → browse open issues

`playwright`

Run browser-based e2e tests for Stellar dApps.

Tools available:
- browser_navigate(url)      → open page
- browser_click(selector)    → click element
- browser_type(selector, text) → fill input
- browser_screenshot()       → capture screen
- browser_evaluate(script)   → run JS in page

When to Use MCP vs Agentic Kit

Task	Use
Query chain data during development	`stellar-rpc` MCP
Check contract state after deploy	`stellar-rpc` MCP
Read/write project files	`filesystem` MCP
Commit and push code	`github` MCP
Run e2e tests	`playwright` MCP
Production frontend blockchain queries	`useStellarData()` hook
Production contract calls from frontend	`useContract().write()` hook

Strict Rules

Use MCP tools during development and debugging only
Production blockchain queries go through useStellarData() — not MCP
Never commit secrets to .mcp.json — use env field with user-provided values
Use stellar-rpc for quick checks; use useStellarData() for built frontend code
The filesystem MCP is the primary way Claude reads/writes project files

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free