
SigRank SignalAF MCP server
Which MCP servers are SigRank SignalAF's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-21
- Registry namecom.signalaf/contribution-exchangeverified in the MCP registry
The registry name sits under signalaf.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-21
- Tools6
- Server calls itselfcontribution-exchange
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-21 the server answered initialize and tools/list without a sign-in. First answer in 738 ms.
- Its tools do none of the product's use cases we checked: compare token efficiency against other operators on leaderboards; calculate yield by pasting token counts; scan local sessions with the npx sigrank tool.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP score67 of 100answers 100 · does the job 0 · definitions 100 · context 100 · use 21 · connects 100
- What an agent can do with it0 of 3 use cases
- Use6 GitHub stars
- Answered100% of days7 of 7 daily checks
- Median first answer873 ms
- Space in an agent's context≈ 1,535 tokensthe definitions of all its tools (6), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 6 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- cannot · compare token efficiency against other operators on leaderboards
- cannot · calculate yield by pasting token counts
- cannot · scan local sessions with the npx sigrank tool
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
exchange_discover_domainDetermine whether a domain publishes a Contribution Exchange profile. Returns the canonical Exchange manifest, policy URLs, signal URLs, and whether the domain is self-hosted or delegated to a Steward. Read-only — does not propose…
exchange_get_policyFetch the canonical Contribution Exchange policy for a domain or its delegated Steward. Returns authority ceilings, consideration limits, human-review requirements, and supported behavior. Read-only — does not mutate state or perform…
exchange_preflightEvaluate a proposed contribution against the same policy logic used by the real proposal flow. Returns whether the proposal is likely to be auto-engaged, accepted for review, escalated to a human, or rejected as invalid. READ-ONLY…
exchange_list_signalsList domain-published Exchange Signals (problems, requests, challenges, bounties, verification tasks, discoveries, experiments). Read-only. Returns canonical URLs, signal revision, revision hash, and status. Signal status is DISTINCT from…
exchange_get_signalGet full detail for a single Exchange Signal by ID. Read-only. Returns the complete signal including constraints, participation rules, verification configuration, consideration declaration, and follow-on behavior. A signal does NOT create…
exchange_get_attemptGet detail for a signal attempt. Read-only. Enforces attempt visibility — actors may only read their own private attempts. Returns attempt status and verification result if available. Attempt status is NOT an exchange state. Verification…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"contribution-exchange": {
"type": "http",
"url": "https://signalaf.com/api/exchange/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http signalaf https://signalaf.com/api/exchange/mcpclaude.ai, ChatGPT and other clients: add https://signalaf.com/api/exchange/mcp as a custom connector in the settings.
- com.signalaf/sigrankanswers, 16 toolsverified in the MCP registry
OpenAPI spec
8 paths, read 2026-10-21. Open the spec ↗
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.