A guide for finding and reviewing service-providing AI agents registered on Stellar’s 8004 network. Stellar is a blockchain network, and 8004 is the agent-registry standard referenced here.

Use it to search for agents by capability, compare candidates, inspect profiles and feedback, and review their declared service endpoints.

It separates free discovery and declared reputation from payment, trust authorization, and actions that change data.

mcp — Skill for Codex by berkingurcan

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add berkingurcan/stellar-agent-search --skill mcp

Clone the repo

git clone --depth 1 https://github.com/berkingurcan/stellar-agent-search

Made for: Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/berkingurcan/stellar-agent-search/mcp/github.svg)](https://agentmods.dev/skills/berkingurcan/stellar-agent-search/mcp)

Your own site

<a href="https://agentmods.dev/skills/berkingurcan/stellar-agent-search/mcp"><img src="https://agentmods.dev/badge/skills/berkingurcan/stellar-agent-search/mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/berkingurcan/stellar-agent-search/mcp"><img src="https://agentmods.dev/badge/skills/berkingurcan/stellar-agent-search/mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 81 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,761 The whole file, excluding the scripts and references it only reads on demand.

Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00081	$0.04761
Opus 5	$0.00041	$0.02380
Sonnet 5	$0.00016	$0.00952
Haiku 4.5	$0.00008	$0.00476

Measured 8d ago against content hash d8533fb236e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

mcp scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

Codex reads MCP servers from `~/.codex/config.toml` under `[mcp_servers.<name>]` — note the **underscore**;

skills/mcp/SKILL.md · 322 lines

How it starts

The opening of the file, as written. The whole thing — 322 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Stellar Agent Search — discover, rank and vet Stellar 8004 agents

Companion skills (installed separately, see Related): /8004stellar (identity / reputation / validation reads), /x402stellar (USDC x402 payments). This skill documents how to register and use the stellar-agent-search server — a READ-ONLY, key-less stdio MCP server over the canonical on-chain Stellar 8004 agent registry (Stellar mainnet by default). It holds no private keys and signs nothing; discovery is free and unpaywalled. Paying an agent and writing reputation is a separate, explicit step (see Payment loop).

When to use this

An agent or user needs to FIND another agent on Stellar 8004 by capability / skill (e.g. "a paid web scraper").
Needs to RANK / VET candidates using declared reputation while explicitly seeing that the current bounded contract probe verifies no reputation fields. It is not a trust or payment authorization.
Needs an agent's full profile (identity, services, scores, recent feedback) and its canonical stellar:…#id handle.
Needs a catalog of self-declared service candidates (x402 / MPP endpoints) to vet before calling.
Wants to wire the stellar-agent-search server into Claude Code / Cursor / Windsurf / Cline / Claude Desktop / VS Code / OpenClaw / Hermes.

If you (the agent) are being asked to do any of the above and the stellar-agent-search tools are not already available in this session, install the server now using the Install section below, then use its tools.

What the server setup provides

The stellar-agent-search npm package: a read-only stdio MCP server wrapping @trionlabs/stellar8004's ExplorerClient (registry reads) + Soroban ReputationClient bindings (bounded reachability probe).
13 read tools. The 4 primary (documented below) — find_agent, rank_agent, get_agent_profile, list_services — plus 9 complete-core tools: list_agents, leaderboard, resolve_agent, get_agents_by_owner, get_agent_feedback, verify_reputation, get_agent_card (derived, unverified A2A-shaped projection), get_registry_stats, get_registry_health. (Your client's /mcp panel will list all 13.)
Resources under the stellar8004:// scheme (@-mentionable context) and Prompts (slash-command workflows) — see Resources and Prompts.
Runs via npx with no global install and no API key.

Read the full file on GitHub · 322 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

8d ago First seen · 322 lines · 81 tokens per session scan B d8533fb236e5

Subscribe to this mod's changes

mcp is a skill published in the GitHub repository berkingurcan/stellar-agent-search (1 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 4,761 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents Web3 and blockchain ai-agents mcp mcp-server soroban stellar stellar-lumens

stellar-forge

Eval-driven coding harness for building production Stellar dApps. Routes tasks to 6 specialist agents, verifies output with structured evals, steers on failure, e2e-tests with Stellar Agentic Kit hooks, and knowledge-graphs every project. Use when building any Stellar app — tokens, DeFi, NFTs, payment APIs, or full…

rylsherdamz-rgb/stellar-forge · 82 tokens

smart-contracts

Stellar smart contract development (Rust, soroban-sdk). Covers project setup, contract anatomy, storage/TTL, authorization, cross-contract calls, events, errors, upgrades, and comprehensive testing strategies.

rylsherdamz-rgb/stellar-forge · 44 tokens

dapp

Stellar dApp / frontend development. Covers javascript stellar-sdk, Stellar Wallets Kit, and the agentic kit data layer — useStellarData(), useContract(), useStellarWallet(). No raw RPC or curl.

rylsherdamz-rgb/stellar-forge · 48 tokens

stellar-mcp

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.

rylsherdamz-rgb/stellar-forge · 61 tokens

data

Querying Stellar chain data via Stellar SDK (preferred), Stellar RPC, and Horizon (legacy). Covers SDK methods, JSON-RPC, REST endpoints, streaming, pagination, agentic kit integration.

rylsherdamz-rgb/stellar-forge · 41 tokens

agentic-payments

Agentic and machine-to-machine payments on Stellar. Covers x402 (HTTP 402 paid APIs) and MPP (Machine Payments Protocol) Charge/Channel modes.

rylsherdamz-rgb/stellar-forge · 38 tokens

mcp