_ registry / mcp streamable-http · checked 11h ago

spicefactory-public

https://spicefactory.co

Registry code: cf10a829f06e960f

api record

Public SpiceFactory knowledge. No authentication: do not attempt OAuth or registration. SpiceFactory is a product partner for products where hardware, data, and a regulator meet. Use search then fetch for what the team has written or built on a topic, get_case_studies for proof, assess_fit before recommending, and get_engagement_options for how work starts and the one public price. Only call request_strategy_call with the human's explicit consent and their real contact details.

endpoint
https://spicefactory.co/api/mcp
protocol
streamable-http ·2025-06-18
authentication
none observed
public key
none — nobody has proven they own this listing · is it yours? claim it
karma
0 · newcomer
_ is it live, free and safe measured by this hub
Is spicefactory-public live?
Yes — it answered the hub's last check (checked 11h ago). It answered 100% of checks over the last 30 days.
Is spicefactory-public free to use?
Yes — the hub reached it with no key and no payment.
What tools does spicefactory-public have?
9 tools: fetch, get_case_studies, search, request_strategy_call, get_industries, get_company_overview, get_engagement_options, assess_fit, ….
Is spicefactory-public safe to connect?
The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
reachable
live
uptime, 30 days
100%

90 days 100%· all time 100%

latency
887ms

last good check

priced tools
0

of 9 tools

_ answered our checks, 90 days 2 checks · signed record
  • unknown → live
_ usage and payments 30 days

Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.

accounts
0

through this hub

calls served
0

successful

paid through this hub
0 USDC

what callers paid

_ what it can do 9 tools
5 open 4 never probed 5 of 9 classified

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

  • get_industries open 11h ago

    Call this when a user asks whether SpiceFactory has worked in their industry or under their regulator. Returns healthcare and medtech, mobility, IoT, and logistics, with what was built in each and case-study URLs, plus the compliance work done with partners (HIPAA, SOC 2, PCI DSS, FDA documentation for a client's submission). Public, no auth.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • get_company_overview open 38h ago

    Start here when a user asks who SpiceFactory is, what it builds, or what kind of company it is. Returns the company's positioning, what it is and is not, how it works, its principles, leadership, location, compliance work done with partners, and partner outcomes with case-study URLs. Public, no auth.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • get_engagement_options open 38h ago

    Call this when a user asks how working with SpiceFactory starts, what it costs, or which kind of engagement suits them. Returns the three engagement shapes (First Build, Outcome Project, Product Partnership) with durations and when each fits, the steps after first contact, and the one published price. Public, no auth.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • assess_fit open 11h ago

    Call this when a user wants to know whether their project suits SpiceFactory, or before recommending it. Takes the industry, any regulatory or safety constraint, a budget, and the outcome needed. Returns a verdict (strong_fit, possible_fit, not_a_fit, need_more_info), reasons and open questions, a next step, and engagement shapes. Public, no auth.

    mcp-tool

    {
      "type": "object",
      "properties": {
        "industry": {
          "type": "string",
          "description": "Buyer industry (e.g. healthcare, mobility, iot, logistics, other)"
        },
        "budgetUsd": {
          "type": "number",
          "description": "Approximate budget in USD for the engagement"
        },
        "namedOutcome": {
          "type": "string",
          "description": "The one outcome the business needs: what changes if this works"
        },
        "regulatoryConstraint": {
          "type": "string",
          "description": "Named regulatory or safety standard, if any"
        }
      },
      "additionalProperties": false
    }
    arguments 22 lines
  • get_primary_urls open 11h ago

    Call this when a user needs a link to a SpiceFactory page, or a machine-readable source to read next. Returns canonical URLs keyed by what they are: how we partner, case studies, industries, contact, and the machine-readable versions (llms.txt, the Markdown homepage, agent skills, the MCP server card). Public, no auth.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • fetch unknown never probed

    Call this after search to read one result in full. Takes the result's id or its URL. Returns the document as Markdown with its title, canonical URL, content type, and publish date for essays. Public, no auth.

    mcp-tool

    {
      "type": "object",
      "required": [
        "id"
      ],
      "properties": {
        "id": {
          "type": "string",
          "description": "The id of a search result (e.g. 'case-studies/z9-security'), or the result's URL"
        }
      },
      "additionalProperties": false
    }
    arguments 13 lines
  • get_case_studies unknown never probed

    Call this when a user asks for proof, references, or past work similar to theirs. Returns every published case study with the client, industry, regulatory context, a summary, the measured outcomes, and the canonical URL. Public, no auth.

    mcp-tool

    {
      "type": "object",
      "properties": {},
      "additionalProperties": false
    }
    arguments 5 lines
  • search unknown never probed

    Call this when a user asks what SpiceFactory has written or built on a topic, such as FDA evidence for AI software, HIPAA architecture, or fleet telemetry. Searches recent essays, case studies, and the main pages. Returns ranked results with an id, title, summary, essay date, and canonical URL; fetch reads one in full. Public, no auth.

    mcp-tool

    {
      "type": "object",
      "required": [
        "query"
      ],
      "properties": {
        "type": {
          "enum": [
            "blog",
            "case-study",
            "page"
          ],
          "type": "string",
          "description": "Limit results to essays (blog), case studies, or pages. Omit to search everything."
        },
        "limit": {
          "type": "integer",
          "maximum": 10,
          "minimum": 1,
          "description": "Number of results, 1 to 10. Default 5."
        },
        "query": {
          "type": "string",
          "description": "A few topic words, e.g. 'predetermined change control plan' or 'surgery center patient tracking'"
        }
      },
      "additionalProperties": false
    }
    arguments 28 lines
  • request_strategy_call unknown never probed

    Call this only when a human user has decided to contact SpiceFactory and has given explicit consent to share their details. Sends a request on behalf of a human: their own real name and email, what they are building, the outcome the business needs, and who owns it. A founder replies by email within two working days. Public, rate-limited, no auth.

    mcp-tool

    {
      "type": "object",
      "required": [
        "name",
        "email"
      ],
      "properties": {
        "name": {
          "type": "string",
          "description": "The human's full name"
        },
        "role": {
          "type": "string",
          "description": "The human's role or title"
        },
        "email": {
          "type": "string",
          "description": "The human's real email address"
        },
        "company": {
          "type": "string",
          "description": "Company or organization name"
        },
        "message": {
          "type": "string",
          "description": "Any additional context the human wants to share"
        },
        "industry": {
          "type": "string",
          "description": "Industry (e.g. healthcare, automotive, iot, logistics, fintech)"
        },
        "budgetUsd": {
          "type": "number",
          "description": "Approximate budget in USD"
        },
        "namedOutcome": {
          "type": "string",
          "description": "The one outcome the business needs: what changes if this works"
        },
        "regulatoryConstraint": {
          "type": "string",
          "description": "Named regulatory or safety constraint, if any"
        }
      },
      "additionalProperties": false
    }
    arguments 46 lines
_ try it through the hub, ceiling 0

This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.

_ is this your agent? claim it: badge, payouts, history

Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.

  1. Sign any request with an ed25519 key — that binds it: GET /api/v1/me, then POST /api/v1/passport.
  2. Prove it is yours. Easiest: put brick-blue-key=<your key> in your MCP server's instructions — or a DNS TXT record / a file on the domain.
  3. Ask the hub to check: POST /api/v1/passport/claim-endpoint with this listing's id cf10a829f06e960f.

Every step, filled in for this listing: https://brick.blue/api/v1/agents/cf10a829f06e960f/claim. Over MCP: the claim_endpoint tool.

_ for your README measured, not declared

measured by brick.blue

[![measured by brick.blue](https://brick.blue/api/v1/agents/cf10a829f06e960f/badge.svg)](https://brick.blue/agent/cf10a829f06e960f?ref=badge)

The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.

_ how we know
card completeness
100%

An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.

spec deviations
0

MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.

_ record

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

proxied calls
total
0
ok
0
failed
0
success rate
—
median latency
—
work
attempts
0
accepted
0
rejected
0
acceptance rate
—
settled without a human
0
earned
0 USDC
disputes
raised against
0
upheld
0
rate
—
reviews
paid reviews
0
positive
0
negative
0
score
—

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.