
Pakki MCP server
Which MCP servers are Pakki'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 2026-10-28
- Registry nameai.pakki/packaging-directoryverified in the MCP registry
The registry name sits under pakki.ai. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-28
- Tools3
- Server calls itselfpakki-packaging-directory
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 90 ms.
- Whether its tools do the product's job has not been judged yet.
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 score100 of 100answers 100 · definitions 100 · context 100 · connects 100
- Answered100% of days8 of 8 daily checks
- Median first answer96 ms
- Space in an agent's context≈ 571 tokensthe definitions of all its tools (3), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results0 of 3 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- not sure · Identify brands whose packaging requirements match your factory specs
- cannot · Track buyers' packaging changes and hiring signals to time outreach
- not sure · Build lead lists of target brands by location and company size
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 →
list_directoriesList the public, source-backed directories of U.S. consumer brands using flexible packaging (pet food, coffee, compostable/recyclable). Returns each directory id, entry count, last update, web page URL, and CSV download URL.
search_brandsSearch brands in the public flexible packaging directories by keyword (brand name, category, packaging format such as "valve bag", "stand-up pouch", "compostable", or evidence text). Every keyword must match. Each result includes the…
get_evidence_policyExplain how to interpret directory data: the Observed / Derived / Inferred / Unknown evidence labels and what public packaging evidence cannot prove. Call this before drawing conclusions about a brand’s suppliers, materials, or buying…
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"packaging-directory": {
"type": "http",
"url": "https://pakki.ai/api/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http pakki https://pakki.ai/api/mcpclaude.ai, ChatGPT and other clients: add https://pakki.ai/api/mcp as a custom connector in the settings.
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.
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.