Fallback MCP server
Commit Oct 6, 2026Provides deterministic recovery and decision utilities for autonomous agents to diagnose failures, repair requests, and find data sources.
Also known as baronsigma/fallback-agent-tools, fallback-agent-tools
- Stars
- 0
- Tools
- 4
- Downloads, 30 days
- —
- Latest version
- 0.1.0-beta.1
- Last commit
- Oct 6, 2026
- License
- MIT
What is Fallback MCP?
Fallback provides deterministic recovery and decision utilities for autonomous agents to diagnose failures, repair requests, and find data sources. It exposes 4 tools, such as source_route, error_route, request_repair.
Summary generated from the project's README
About Fallback MCP server
Fallback provides a suite of deterministic utilities designed to help autonomous agents navigate failures and decision points. Instead of relying on expensive reasoning loops when an agent gets stuck, these tools offer small, specialized functions to diagnose errors or find data. The service is available as a hosted MCP endpoint or via an HTTP API, utilizing an x402 V2 pay-per-call model on the Base mainnet with canonical USDC. No accounts or API keys are required, as users approve payments for each specific tool call.
Developers can use specific tools like source_route to find machine-readable data formats, error_route to classify failed requests, request_repair to suggest minor fixes based on evidence, and stop_search to determine if further investigation is worth the cost. The system is built for precision, offering bounded actions such as finding an API or dataset from a specific domain. Each tool call has defined limits, such as a maximum of 8 direct HTTP requests and 12 seconds of total execution time per call.
What you can do with it
- 1Locate machine-readable data sourcesAn agent can identify the best way to access a specific dataset in JSON or CSV format from a known publisher.
- 2Diagnose and recover from request failuresWhen an API or tool call fails, the agent can classify the error to determine the next safe action.
- 3Repair malformed requestsThe agent can propose minimal changes to a request using available evidence to make it valid.
- 4Optimize search expendituresAn agent can decide if continuing a search is economically justified based on current evidence.
Written from the project's README. Every use case is checked against a quote from it.
How to install Fallback MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Fallback MCP in Claude Code
$ claude mcp add --transport http fallback-agent-tools https://fallback.factrail.online/mcpInstall Fallback MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"fallback-agent-tools": {
"url": "https://fallback.factrail.online/mcp"
}
}
}Install Fallback MCP in VS Code
.vscode/mcp.json
{
"servers": {
"fallback-agent-tools": {
"type": "http",
"url": "https://fallback.factrail.online/mcp"
}
}
}Install Fallback MCP in VS Code CLI
$ code --add-mcp '{"name":"fallback-agent-tools","type":"http","url":"https://fallback.factrail.online/mcp"}'Install Fallback MCP in Codex
$ codex mcp add fallback-agent-tools --url https://fallback.factrail.online/mcpInstall Fallback MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.fallback-agent-tools] url = "https://fallback.factrail.online/mcp"
Install Fallback MCP in Gemini CLI
$ gemini mcp add -s user --transport http fallback-agent-tools https://fallback.factrail.online/mcpInstall Fallback MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"fallback-agent-tools": {
"url": "https://fallback.factrail.online/mcp",
"type": "http"
}
}
}Fallback MCP tools 4
Detected from the READMEsource_routeerror_routerequest_repairstop_search
| source_route | — | |
| error_route | — | |
| request_repair | — | |
| stop_search | — |
Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablebaronsigma/fallback-agent-tools is public and reachablegithub.com/baronsigma/fallback-agent-tools ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-10-06github.com/baronsigma/fallback-agent-tools ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model4 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeinitialize answered with protocol 2025-06-18 in 490 msPass
README
View on GitHubFallback
______ _ _
| ____| | | |
| |__ __ _ | | |__ __ _ ___| | __
| __|/ _` || | '_ \ / _` |/ __| |/ /
| | | (_| || | |_) | (_| | (__| <
|_| \__,_||_|_.__/ \__,_|\___|_|\_\
find the route forward
Fallback
Tiny paid recovery and decision utilities for autonomous agents.
When an agent gets stuck, Fallback helps it find the next safe move without wasting a large reasoning loop.
source_route Where should I look? ($0.02)
error_route Why did this fail? ($0.002)
request_repair Can I safely fix the request? ($0.005)
stop_search Is another search worth it? ($0.003)
Use Fallback
Pay-per-call tools that help AI agents find sources, diagnose failures, repair requests, and decide when to stop searching. Fallback gives autonomous agents small, deterministic utilities for the moments where automation gets stuck: finding the right source, diagnosing a failed request, repairing a request from available evidence, and deciding whether another search or paid retrieval is worth the cost.
Hosted service
MCP endpoint: https://fallback.factrail.online/mcp\
HTTP API base: https://fallback.factrail.online\
Payment: x402 V2 pay-per-call. Check each live challenge for network, asset, amount, and recipient.
Agent skill: skill.md
OpenAPI: openapi.json
Network: Base mainnet, canonical USDC
Release: v0.1.0-beta.1
Tools
source_route($0.02): Where should I look? Find likely authoritative or machine-readable sources.error_route($0.002): Why did my call fail? Classify a failed request and recommend a bounded next action.request_repair($0.005): Can I safely fix the request? Propose the smallest change supported by caller-supplied evidence.stop_search($0.003): Is further searching worth it? Decide whether more bounded search effort is justified by the evidence and remaining cost.
These tools do not replace agent reasoning, and stop_search never proves universal absence.
When an agent should use this
Use source_route when an agent knows what it needs and which publisher (a domain or start URL), but not how to get it in machine-readable form: an API, OpenAPI spec, bulk download, dataset or feed.
- Good fit: "Get the latest population dataset from Eurostat", "Find a JSON/CSV route for this agency's statistics", before the agent starts browsing page by page.
- Not a fit: general web research, answering a factual question, or verifying a fact (for source-backed facts, see FACTRAIL MCP).
How to read the result:
status: routes_found: try routes in order.scoreis a deterministic ranking, not a probability or confidence.status: no_suitable_route_found: nothing suitable within the checked scope (seechecked.direct_probes). This is not evidence that no route exists. The agent should look elsewhere (another host, the publisher's open-data portal), not conclude "there is no API".- Always read
limitations. It says, for example, whether external search was unavailable or candidate inspection was capped.
Limits per call: at most 8 direct HTTP requests, 12 s total, 1 MiB per response, and at most 1 external search request. No LLM inference. The hosted beta currently runs deterministic discovery only (no search provider configured).
Access: hosted MCP https://fallback.factrail.online/mcp (Streamable HTTP) or the HTTP tool routes, x402 pay-per-call (each challenge declares its payment network and amount; no account or API key). To try it without payment, self-host with PAYMENT_MODE=disabled (see Local development). Machine-readable summary: llms.txt. More detail: Using Fallback with agents.
Fallback is publicly launched. See the current launch and distribution status, product rename impact audit, discovery/distribution readiness audit, and telemetry and 30-day KPI definitions.
When to use error_route
Use it after an HTTP, API, MCP, or tool request fails when the safe next action is unclear. It classifies supplied evidence and returns bounded retry guidance. Do not use it when recovery is already obvious or the task needs deeper domain reasoning; it does not execute requests or invent undocumented fixes.
Requirements
- Current Node.js LTS (Node 24 at scaffold creation; supported engine is Node 22+)
- npm
Local development
npm install
cp .env.example .env
npm run generate
npm run dev
The server exposes /, /healthz, /readyz, /catalog.json, /openapi.json, /llms.txt, /llms-full.txt, /skill.md, /.well-known/x402.json, /.well-known/mcp/server-card.json, and the Streamable HTTP MCP endpoint at /mcp. Both HTTP and MCP dispatch through the shared runtime handler registry. PAYMENT_MODE=disabled supports local development; paid deployments must explicitly select test or production and provide complete x402 configuration.
Verification
npm test
npm run typecheck
npm run lint
npm run benchmark:source-route
npm run benchmark:error-route
npm run verify:catalog
npm run release:check
30-second start
Connect an x402-compatible agent to https://fallback.factrail.online/mcp, call the matching tool after a concrete failure or search decision, and approve only the network, token, recipient, and amount shown by its payment challenge. HTTP clients can use POST /v1/tools/{tool_id} on the hosted origin. See skill.md for examples and schemas.
Architecture
src/core/registry.ts is the one canonical tool registry. Every discovery surface and distribution artifact is derived from it. Each tool gets a directory under src/tools/ with a contract and handler; future tool tests and fixtures belong alongside the matching contract test/fixture directories. HTTP and MCP adapters must call the same tool handler. Payment middleware and marketplace integrations stay outside tool logic.
The service supports x402 V2 per-call payment without accounts or API keys. The server only receives payment at X402_PAY_TO; no receiving wallet private key is required. Paid startup fails closed if the required network, receiving address, facilitator URL, or production URL is missing or invalid. See deployment and payment setup.
Example
{
"goal": "Download the latest population dataset",
"start_url": "https://ec.europa.eu/eurostat/",
"preferred_formats": ["csv", "json"]
}
Call POST /v1/tools/source_route with a goal and either start_url or domain. The result is limited to the checked scope; a missing result does not mean that no route exists. Direct site discovery runs without external search credentials. If Tavily or Brave is configured and direct discovery is insufficient, the tool can make at most one search request.
See PRODUCT, ARCHITECTURE, TOOL_ADMISSION, DISTRIBUTION, and RELEASE.
Related: FACTRAIL MCP
Fallback comes from the same author and design rule as FACTRAIL MCP: agent tools should report what they checked, not only what they found. FACTRAIL answers "what is established about this fact, and from which source?" by returning evidence envelopes with support levels, unresolved fields and receipts ("unknown is better than invented"). Fallback answers "where can I get this data?" ("absence is not proof of nonexistence"). The two are independent services with no code dependency, and you can use either one alone.
Fallback MCP questions
How do I add Fallback MCP to Claude Code?
Run claude mcp add --transport http fallback-agent-tools https://fallback.factrail.online/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Fallback MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Fallback MCP provide?
It exposes 4 tools, including source_route, error_route, request_repair, stop_search.
What can the source_route tool do?
It helps agents find likely authoritative or machine-readable sources like APIs, OpenAPI specs, or datasets when they know the publisher but not the specific data route.
How does the error_route tool help an agent?
It classifies why a request failed and recommends a bounded next action to help the agent recover.
Does the stop_search tool prove that information does not exist?
No, the tool decides if further searching is worth the cost, but it never proves universal absence.
How is payment handled for these tools?
The service uses x402 V2 pay-per-call, where the agent approves the network, asset, amount, and recipient shown in a payment challenge.