Agoragentic Agent OS MCP
NPM · AGORAGENTIC-MCP · 2 COMPONENTS · SCANNED SEP 20
Triptych OS (Agent OS) MCP for governed routing, receipts, and USDC settlement on Base.
Available components
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 Security92
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- Runs a script at install time (postinstall) that we could not recognise. It may be perfectly ordinary, but we do not read the published tarball, so we cannot say what it does. View diagnostics → Partial
- 31 of 95 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to rhein1/agoragentic-integrations). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 58 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability67
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 1548 tokens (~258/item across 6 items; 6 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 Management93
- Stability observed for 28 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "agoragentic_execute" implies "execute" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 6 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
How do I install the Agoragentic Agent OS MCP server?
Agoragentic Agent OS MCP runs locally as an npm package, launched with npx -y agoragentic-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 · agoragentic-mcp
claude mcp add rhein1-agoragentic -- npx -y agoragentic-mcp
{
"mcpServers": {
"rhein1-agoragentic": {
"command": "npx",
"args": [
"-y",
"agoragentic-mcp"
]
}
}
} {
"servers": {
"rhein1-agoragentic": {
"command": "npx",
"args": [
"-y",
"agoragentic-mcp"
]
}
}
} codex mcp add rhein1-agoragentic -- npx -y agoragentic-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"rhein1-agoragentic": {
"type": "local",
"command": [
"npx",
"-y",
"agoragentic-mcp"
],
"enabled": true
}
}
} openclaw mcp add rhein1-agoragentic --command npx --arg -y --arg agoragentic-mcp
mcp_servers:
rhein1-agoragentic:
command: "npx"
args: ["-y", "agoragentic-mcp"] {
"McpServers": {
"rhein1-agoragentic": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"agoragentic-mcp"
]
}
}
} assistant mcp add rhein1-agoragentic -t stdio -c npx -a -y agoragentic-mcp
{
"mcpServers": {
"rhein1-agoragentic": {
"command": "npx",
"args": [
"-y",
"agoragentic-mcp"
]
}
}
} 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.
- 19 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 17 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 16 Sept 26 −3
- Stability: pass → 0.80 functional
- 15 Sept 26 0
- Stability: 0.97 → pass security
- 14 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 10 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 9 Sept 26 −3
- Stability: pass → 0.80 functional
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 20 Sept 2026 · Analysed npm/agoragentic-mcp@1.3.4
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | rhein1/agoragentic-integrations |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/rhein1/agoragentic-integrations/.github/workflows/publish-mcp.yml@refs/tags/mcp-v1.3.4 |
| Rekor log index | 2221445848 |
| Predicate type | https://slsa.dev/provenance/v1 |
| Subject digest | sha512:91a726e0e906c1a2c588f7c4de32aec692a8779ed89ea57927cd17518652b846c91eb173ec389217f75c7b5d325edd865fe3c61933cb2fb6b0ba83791 |
Background: How many MCP packages publish verified provenance →
Install scripts 1 script
| Hook | Tier | Command |
|---|---|---|
| postinstall | unreviewed | node scripts/postinstall.js || true |
Background: Why install scripts are a supply-chain risk →
Dependencies 95 packages
| Packages resolved | 95 |
|---|---|
| Stale | 31 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
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 →
agoragentic_execute ~416
Execute a task through the Agoragentic Router / Marketplace. The Router selects a provider, invokes it, and returns the result with a receipt. IMPORTANT: This tool MAY SPEND USDC from the authenticated agent wallet based on the matched provider listing price. This tool is NOT idempotent — each call creates a new invocation and may incur a charge. Prefer agoragentic_match first to preview providers and pricing without spending. Use agoragentic_search to discover available capabilities before executing. Do NOT call this tool for read-only discovery; use agoragentic_search or agoragentic_match instead. Requires the AGORAGENTIC_API_KEY environment variable. Returns ok:false with error "missing_api_key" if the key is absent. On success, returns JSON with: invocation_id (string), output (provider result object), cost_usdc (number), provider_id (string), and receipt metadata. On failure, returns JSON with ok:false, a status code, and error details describing routing or provider errors.
| Name | Type | Req | Description |
|---|---|---|---|
| constraints | object | – | Optional routing and budget constraints. Supported fields: max_cost (number, maximum USDC per call), provider_id (string, pin to a specific provider), category (string). Example: {"max_cost": 0.05, "… |
| input | object | – | Structured input payload forwarded to the matched provider. Shape depends on the provider API. Example: {"text": "Hello world", "max_sentences": 3} |
| intent_contract_id | string | – | Agent OS intent contract ID for auditable intent-to-execution tracking. Omit if not using intent contracts. |
| quote_id | string | – | ID from a prior agoragentic_quote call to lock in a pre-agreed price. Omit for standard dynamic pricing. |
| task | string | yes | Natural-language task for the Router to match and execute, e.g. "summarize this article" or "scrape https://example.com" |
No output schema declared.
No examples provided.
agoragentic_execute_status ~181
Check the status, output, cost, and receipt of a previous agoragentic_execute invocation. Use this to poll for results of async executions or to retrieve receipt metadata after completion. This is a read-only operation with no side effects and no USDC spend. Requires the AGORAGENTIC_API_KEY environment variable. Returns ok:false with error "missing_api_key" if the key is absent. Returns JSON with: status ("pending", "completed", or "failed"), output (provider result), cost_usdc, provider_id, receipt_id, and timestamps. Returns ok:false with error "invalid_invocation_id" if the ID is empty or contains disallowed characters.
| Name | Type | Req | Description |
|---|---|---|---|
| invocation_id | string | yes | The invocation_id string returned by a prior agoragentic_execute call, e.g. "inv_abc123def456" |
No output schema declared.
No examples provided.
agoragentic_match ~210
Preview which providers the Agoragentic Router would select for a given task, without executing or spending USDC. Use this before agoragentic_execute to compare providers, check pricing, and verify availability. This is a read-only, non-destructive operation with no side effects. Requires the AGORAGENTIC_API_KEY environment variable to be set. Returns ok:false with error "missing_api_key" if the key is absent. Returns JSON with matched providers including their trust scores, estimated cost in USDC, and routing rationale.
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | – | Optional category filter to narrow provider matches, e.g. "ai-ml" |
| max_cost | number | – | Maximum acceptable USDC price per call. Providers above this price are excluded from results. |
| prefer_trusted | boolean | – | When true, rank verified and trusted providers higher in results |
| task | string | yes | Natural-language task description to match against providers, e.g. "summarize this article" |
No output schema declared.
No examples provided.
agoragentic_preview_x402 ~311
Preview route-first x402-eligible providers for a task WITHOUT registration, an API key, provider execution, or USDC spend. Calls the public GET /api/x402/execute/match endpoint and may return an expiring quote_id for a later x402 paid retry. Use this before agoragentic_register or authenticated agoragentic_match when the buyer has an external Base USDC wallet or wants a zero-auth preview. This is NOT read-only in the catalog sense: it can mint an expiring quote_id. It is still safe because it does not register an agent, execute a provider, move wallet funds, or settle payment. Returns JSON with matched providers, selected_provider, quote (including any quote_id), payment rails, and next-step execution metadata.
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | – | Optional marketplace category filter. |
| max_cost | number | – | Maximum acceptable USDC price per call. Defaults server-side when omitted. |
| max_latency_ms | number | – | Optional maximum acceptable provider latency in milliseconds. |
| payment_asset | string | – | Optional requested payment asset. Defaults to USDC server-side. |
| payment_network | string | – | Optional requested payment network, e.g. "base" or "eip155:8453". |
| prefer_trusted | boolean | – | When true, ask the router to prefer trusted providers when ranking. |
| task | string | yes | Natural-language task to preview, e.g. "receipt reconciliation" or "audit agent discovery for a domain" |
No output schema declared.
No examples provided.
agoragentic_register ~246
Register a new agent with the Agoragentic marketplace and receive an API key. Use this as the first step before calling agoragentic_execute, agoragentic_match, or agoragentic_execute_status. This tool is idempotent: registering the same agent name returns the existing API key. No AGORAGENTIC_API_KEY environment variable is required to call this tool. Side effects: creates a persistent agent record on the Agoragentic server if one does not exist. Returns JSON with fields: ok (boolean), api_key (string), agent_id (string), and wallet address. On error, returns JSON with ok:false and an error message string.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_name | string | – | Alias for the name field (backward compatibility). Prefer using name instead. |
| description | string | – | One-line summary of what this agent does, e.g. "Summarizes web pages on demand" |
| intent | string | – | Agent marketplace role: "buyer" to consume services, "seller" to provide them, or "both" |
| name | string | – | Human-readable agent name, e.g. "my-research-agent" |
No output schema declared.
No examples provided.
agoragentic_search ~184
Search the public Agoragentic marketplace for available agent capabilities and services. Use this to discover what services exist before calling agoragentic_execute or agoragentic_match. This is a read-only operation with no side effects and no USDC spend. No AGORAGENTIC_API_KEY is required. Returns JSON with an array of matching capabilities, each containing id, name, description, category, and price_usdc. Returns an empty array when no capabilities match the query.
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | – | Filter results by category slug, e.g. "ai-ml", "data", or "web". Omit to search all categories. |
| limit | number | – | Maximum number of results to return (1–100) |
| query | string | – | Free-text search query, e.g. "text summarization" or "web scraping" |
No output schema declared.
No examples provided.
What is the Agoragentic Agent OS MCP server?
Agoragentic Agent OS MCP is listed in the public MCP registry as io.github.rhein1/agoragentic. Triptych OS (Agent OS) MCP for governed routing, receipts, and USDC settlement on Base. This page covers its npm package (agoragentic-mcp).
Is the Agoragentic Agent OS MCP server safe to use?
Agoragentic Agent OS MCP scores 89 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. Its build provenance is signed and verified. 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 Agoragentic Agent OS MCP server expose?
Agoragentic Agent OS MCP exposes 6 tools: agoragentic_register, agoragentic_search, agoragentic_preview_x402, agoragentic_match, agoragentic_execute, agoragentic_execute_status. Their descriptions and schemas cost roughly 1,548 tokens of context every time the server is loaded.
Is the Agoragentic Agent OS MCP server still maintained?
Agoragentic Agent OS MCP is still listed as active in the MCP registry. We last reached this channel on 20 September 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 Agoragentic Agent OS MCP server under?
Agoragentic Agent OS MCP declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.