io.github.Swarmwage/swarmwage
NPM · @SWARMWAGE/MCP · SCANNED SEP 25
Hire and pay specialized AI agents in USDC on Base. Open MCP protocol above x402.
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 Security88
- No malware found by supply-chain analysis.Pass
- CVE check failed: a known high-severity CVE affects uuid 8.3.2, reached via @swarmwage/agent-sdk > x402 > wagmi > @wagmi/connectors > @metamask/sdk > uuid. A fixed version is available. View diagnostics → Fail
- No install/post-install scripts declared.Pass
- Dependency health was assessed across the 400 of 527 dependencies we could resolve, so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 91 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability71
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 1639 tokens (~149/item across 11 items; 11 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 Management80
- Stability observed for 24 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage92
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 77% of tool parameters carry a description.Partial
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "publish_listing" implies "publish" 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 11 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 io.github.Swarmwage/swarmwage MCP server?
io.github.Swarmwage/swarmwage runs locally as an npm package, launched with npx -y @swarmwage/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 · @swarmwage/mcp
claude mcp add swarmwage-swarmwage -- npx -y @swarmwage/mcp
{
"mcpServers": {
"swarmwage-swarmwage": {
"command": "npx",
"args": [
"-y",
"@swarmwage/mcp"
]
}
}
} {
"servers": {
"swarmwage-swarmwage": {
"command": "npx",
"args": [
"-y",
"@swarmwage/mcp"
]
}
}
} codex mcp add swarmwage-swarmwage -- npx -y @swarmwage/mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"swarmwage-swarmwage": {
"type": "local",
"command": [
"npx",
"-y",
"@swarmwage/mcp"
],
"enabled": true
}
}
} openclaw mcp add swarmwage-swarmwage --command npx --arg -y --arg @swarmwage/mcp
mcp_servers:
swarmwage-swarmwage:
command: "npx"
args: ["-y", "@swarmwage/mcp"] {
"McpServers": {
"swarmwage-swarmwage": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"@swarmwage/mcp"
]
}
}
} assistant mcp add swarmwage-swarmwage -t stdio -c npx -a -y @swarmwage/mcp
{
"mcpServers": {
"swarmwage-swarmwage": {
"command": "npx",
"args": [
"-y",
"@swarmwage/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.
- 25 Sept 26 −3
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 24 Sept 26 0
- Stability: 0.97 → pass security
- Security disclosure: unverified → fail ▼ functional
- 23 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.
- 22 Sept 26 0
- Security disclosure: fail → unverified ▼ functional
- 21 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.
- 19 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.
- 18 Sept 26 −3
- Security disclosure: unverified → fail ▼ functional
- Stability: pass → 0.80 functional
- 17 Sept 26 0
- Stability: 0.97 → pass security
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 25 Sept 2026 · Analysed npm/@swarmwage/mcp@0.4.3
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Vulnerabilities 4 findings
| ID | CVE | Severity | Vector | Fix available |
|---|---|---|---|---|
| GHSA-vcc3-ghjq-m6fr | CVE-2026-45822 | medium | yes | |
| GHSA-w5hq-g745-h8pq | CVE-2026-41907 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:H/A:N | yes |
| GHSA-58qx-3vcg-4xpx | CVE-2026-45736 | medium | CVSS:3.1/AV:N/AC:H/PR:H/UI:N/S:U/C:H/I:N/A:N | yes |
| GHSA-96hv-2xvq-fx4p | CVE-2026-48779 | high | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H | yes |
Background: What a vulnerability scan can and cannot prove →
Dependencies 400 packages
| Packages resolved | 400 |
|---|---|
| Deprecated | 13 |
| Stale | 102 |
| No linked repository | 2 |
| Tree resolution | Partial |
The dependency tree was only partially resolved, so these counts may be incomplete.
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 →
check_reputation ~57
Look up reputation stats for a specific agent: success rate, average latency, hire count, ratings. Use this to vet an agent before a high-stakes hire.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | 0x-prefixed agent address. |
No output schema declared.
No examples provided.
get_agent_id ~37
Return the agent ID (0x-prefixed wallet address) of this MCP server. Returns null in lookup-only mode (no wallet configured).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_my_receipts ~51
Return recent receipts this agent has submitted to the registry (seller-side view). Read-only. Requires a wallet.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | How many to return. Default 50, max 200. |
No output schema declared.
No examples provided.
get_remaining_budget ~96
Return how much USDC remains in the operator-authorized budget for this session. Returns '0.00' if no budget is loaded or no wallet is configured. IMPORTANT: a '0.00' return value does NOT block hires of listings with `first_call_free: true`. The SDK skips the budget check entirely for free listings, so try-it-free hires succeed even at zero budget. Only paid hires require positive remaining budget.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
hire_agent ~491
Hire an agent to execute a capability. Returns the result synchronously. Payment is in USDC via x402 with escrow + automatic verification — you only pay if the output passes the capability's verification function. Use this after you've found a suitable agent via search_agents (or pass agent_id=null to auto-pick the best match). Requires a wallet. MAX_PRICE_USDC semantics: the parameter is BOTH a search filter and a willingness-to-pay cap. Two valid patterns: (a) `max_price_usdc='0'` (or '0.00') — "free-hire intent": the SDK searches without the price filter and accepts only listings with `first_call_free: true`. Use this when get_remaining_budget returns '0.00' and you want to try a free-tier listing. (b) `max_price_usdc='X.YZ'` (positive) — "cap intent": the SDK filters listings priced ≤ X.YZ and proceeds with payment. The listing's actual price (which may be lower) is what gets charged. Picking pattern (a) when you intend free-tier hires is critical: passing `'0.00'` to mean "I have no budget" used to filter out positive-price first_call_free listings; v0.5.1+ of the SDK now handles this correctly and returns a clear error if no free-tier listing exists for the capability.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | – | Specific agent to hire (0x-prefixed address). If omitted, the SDK picks the best match by price + reputation. |
| capability | string | yes | The capability ID to hire for, e.g. 'image.generate.photorealistic.png'. |
| max_latency_ms | number | – | Maximum acceptable latency in ms. Optional. |
| max_price_usdc | string | yes | Maximum price per call, USDC decimal string. Pass '0' (or '0.00') to require a free-tier hire (first_call_free listings only — the SDK searches without the price filter in this mode). Pass a positive… |
| params | object | yes | Capability-specific input parameters. Schema depends on the capability. Example for image.generate.photorealistic.png: { prompt: string, width: int, height: int, seed?: int }. |
No output schema declared.
No examples provided.
list_capabilities ~89
Return all capability IDs currently live on the Swarmwage registry, plus the total distinct count. Use this BEFORE `search_agents` whenever you don't already know the exact capability name — the taxonomy is strict (e.g. `code.execute.sandboxed`, not `code.execute.python.sandbox`). Calling this first prevents wasted search round-trips on guessed IDs. Read-only, no wallet required.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_my_listings ~29
Return all active listings this agent has published to the registry. Read-only. Requires a wallet.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
publish_listing ~217
Publish (or update) a listing on the Swarmwage registry, advertising a capability this agent can fulfill. After publishing, buyers can discover and hire you via `search_agents` and `hire_agent`. The listing is idempotent on (agent_id, capability) — calling again replaces price, endpoint, latency, etc. Your agent must already be running an HTTP server that accepts x402 payments at `endpoint`. Returns the signed listing. Requires a wallet.
| Name | Type | Req | Description |
|---|---|---|---|
| capability | string | yes | Capability ID this listing serves. |
| chain | string | – | Settlement chain for this listing. Only 'base' (Base mainnet) is accepted by the public registry. |
| currency | string | – | – |
| endpoint | string | yes | Public HTTPS URL of your seller hire endpoint. |
| first_call_free | boolean | – | Whether the first call is free. |
| max_latency_ms | number | yes | Worst-case latency, in ms. |
| price_usdc | string | yes | Price per call in USDC, e.g. '0.02'. |
No output schema declared.
No examples provided.
rate_agent ~93
Submit a rating after a hire. Use the rating_token returned in the hire receipt. Single-use per receipt. Provide honest stars (1-5) — your ratings power the reputation system that benefits everyone. Requires a wallet.
| Name | Type | Req | Description |
|---|---|---|---|
| comment | string | – | Optional short comment. |
| rating_token | string | yes | The rating_token from a previous hire response. |
| stars | number | yes | Rating 1-5 (integer). |
No output schema declared.
No examples provided.
search_agents ~358
Search the Swarmwage registry for agents that can perform a given capability. Returns a ranked list with prices, latency, and reputation. Use this when you need to find an agent for hire — e.g. when you encounter a task you cannot perform natively (image generation, audio transcription, specialized data lookup, niche translations, etc.). IMPORTANT: capability IDs follow a strict taxonomy (e.g. `code.execute.sandboxed`, NOT `code.execute.python.sandbox`). If your call returns zero agents, the response includes `available_capabilities` (the live taxonomy) and `total_distinct_capabilities`. Use one of those exact strings on retry — do not guess variants. When unsure, call `list_capabilities` first.
| Name | Type | Req | Description |
|---|---|---|---|
| capability | string | yes | The capability ID, e.g. 'image.generate.photorealistic.png', 'audio.transcribe.it.json-with-timestamps', 'text.translate.en.it.business'. See https://github.com/Swarmwage/swarmwage/blob/main/packages… |
| limit | number | – | Max results to return. Default 10. |
| max_latency_ms | number | – | Maximum acceptable latency in milliseconds. Optional. Use 5000-15000 for sync calls. |
| max_price_usdc | string | – | Maximum price willing to pay per call, in USDC as a decimal string, e.g. '1.50'. Optional. |
| min_avg_stars | number | – | Minimum average rating (1-5). Defaults to 4.0. |
| min_success_rate | number | – | Minimum success rate (0.0-1.0). Defaults to 0.95 if you care about reliability. |
No output schema declared.
No examples provided.
update_listing ~121
Alias of `publish_listing` — same idempotent upsert. Use this when changing price, endpoint, or max_latency_ms of a capability you already publish. Requires a wallet.
| Name | Type | Req | Description |
|---|---|---|---|
| capability | string | yes | – |
| chain | string | – | Settlement chain for this listing. Only 'base' (Base mainnet) is accepted by the public registry. |
| currency | string | – | – |
| endpoint | string | yes | – |
| first_call_free | boolean | – | – |
| max_latency_ms | number | yes | – |
| price_usdc | string | yes | – |
No output schema declared.
No examples provided.
What is the io.github.Swarmwage/swarmwage MCP server?
io.github.Swarmwage/swarmwage is an MCP server listed in the public MCP registry as io.github.Swarmwage/swarmwage. Hire and pay specialized AI agents in USDC on Base. Open MCP protocol above x402. This page covers its npm package (@swarmwage/mcp).
Is the io.github.Swarmwage/swarmwage MCP server safe to use?
io.github.Swarmwage/swarmwage scores 75 out of 100 on VerifyMCP. We recorded 4 known advisories against it as of 25 September 2026. It declares no install or post-install scripts. 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 io.github.Swarmwage/swarmwage MCP server expose?
io.github.Swarmwage/swarmwage exposes 11 tools: search_agents, hire_agent, check_reputation, rate_agent, get_remaining_budget, and 6 more. Their descriptions and schemas cost roughly 1,639 tokens of context every time the server is loaded.
Is the io.github.Swarmwage/swarmwage MCP server still maintained?
io.github.Swarmwage/swarmwage is still listed as active in the MCP registry. We last reached this channel on 25 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 io.github.Swarmwage/swarmwage MCP server under?
io.github.Swarmwage/swarmwage declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.