unfragile
Server Details
Find the AI infrastructure or agent tool for a task, labelled by our checks, with signed receipts.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- Savirinc/unfragile-mcp-server
- GitHub Stars
- 2
- Server Listing
- unfragile-mcp-server
- ChatGPT
- –
- Claude
- Unfragile
TDQS
Scored across 4 tools
find and resolve have a reasonably clear split (broad discovery vs. one qualifying record for a task), but resolve, verify and passport all return the same Ed25519-signed passport for a single record and differ only in framing (verdict + install line vs. verdict only vs. raw JSON), which invites misselection. The descriptions give hints, but an agent must read carefully to know whether to call resolve or verify for a given lookup.
All four tools share the unfragile_ prefix and a short, uniform single-word style (find, resolve, verify, passport), which reads as one predictable family. The only deviation is passport, a noun among three verbs, a minor break in the verb_noun pattern.
Four tools is compact and each maps to a step in the trust workflow: discover, resolve, verify, fetch raw passport. It is on the small side but nothing feels padded or missing at the top level.
The surface covers the core loop of finding a tool, getting a verdict, resolving an installable pick, and pulling the raw signed artifact for offline policy checks. Minor gaps exist: no batch verification of multiple packages, no way to refresh or stream check status, and no listing/browse operation independent of a task query.
Available Tools
4 toolsunfragile_findFind the AI infrastructure or tool action for a taskARead-onlyInspect
Finds the product, and the specific tool action, that does a task, across AI infrastructure (search APIs, models, inference, browsers, harnesses, compute) and the MCP servers, APIs, CLIs, SDKs and models in our index. Each result carries the label from our checks (verified and signed · official · checked: not enough evidence yet · found in code, not yet checked · demo or tutorial · failed its last check) and a signed receipt. answer: true adds a written, cited answer; false returns the ranked list. A fact we hold (a price, a limit, a model id) arrives in structuredContent.blocks (type 'fact') and at the start of the answer, never in results.
Inputs: task (required), kind, lane, limit, +7 more.
unfragile_passportFetch a record's signed trust passportARead-onlyInspect
Fetch the raw Ed25519-signed trust passport JSON for a record (by record page slug, record id, or npm package). For programmatic policy checks; verify offline against the published public key.
Inputs: slug (required).
unfragile_resolveResolve one task to one checked recordBRead-onlyInspect
Returns one checked record for a task, with its verdict, its Ed25519-signed passport and a paste-ready install line, or says that nothing qualifies.
Inputs: intent (required).
unfragile_verifyVerify a tool, MCP server or package before invoking itARead-onlyInspect
Returns our verdict on a tool, MCP server or package (trusted · caution · unverified · flagged) and the reason, with its Ed25519-signed passport, checkable offline against https://unfragile.ai/api/v1/trust-passport-public-key. A flagged verdict means it failed our checks.
Inputs: target (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
AI agent infrastructure for discovery, authorization, execution, identity, and signed receipts.
AI-agent trust infrastructure for discovery, authority, execution, verification, and receipts.
Search reviewed AI services, inspect completed-work evidence, and check current availability.
Agent routing, safety preflight, execution receipts, best execution and verified outcomes.
Related MCP Servers
- AlicenseAqualityBmaintenanceCryptographic accountability for AI agents. Ed25519-signed receipts for every MCP tool call. Constraints, chains, AI judgment, invoicing, and local dashboard included.241MIT
- AlicenseNot gradedqualityBmaintenanceTrust layer for agent work: verify the artifact an AI agent produced, meter what the run actually cost, and keep the agent inside its mandate. Signed receipts verify offline. 20 checks/day free, then 0.005 USDC per call or $49 per environment per month. Locales: en, hi.MIT
- AlicenseAqualityCmaintenanceEnables AI agents to create cryptographically verifiable receipts of their delegated work, with capabilities for multi-party approval and offline verification.1166 npmApache 2.0

garlofficial
AlicenseNot gradedqualityFmaintenanceCryptographic verification for AI agent actions — ECDSA-secp256k1 signed Action Receipts anchored on Base, multi-dimensional trust vectors, capability tokens, and offline-verifiable on-chain proof. 29 tools.2Apache 2.0
Glama MCP Gateway
Add one secure layer between your agents and this server.