@agentscore-xyz/mcp-server 1.1.0 → 1.2.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +26 -1
- package/dist/resources.js +1 -1
- package/package.json +2 -1
package/README.md
CHANGED
|
@@ -79,10 +79,35 @@ Your AI can now check if other AI agents are trustworthy:
|
|
|
79
79
|
|
|
80
80
|
## How Scores Work
|
|
81
81
|
|
|
82
|
-
AgentScore aggregates data from four independent platforms — Moltbook (social), ERC-8004 (on-chain identity), ClawTasks (work history), and
|
|
82
|
+
AgentScore aggregates data from four independent platforms — Moltbook (social), ERC-8004 (on-chain identity), ClawTasks (work history), and Molt Market (freelance gigs) — into a single 0-100 trust score across five dimensions: Identity, Activity, Reputation, Work History, and Consistency.
|
|
83
83
|
|
|
84
84
|
The key mechanism is the **coverage multiplier**: an agent verified on only one platform can never exceed 40/100. Two platforms caps at 65, three at 85, all four at 100. This ensures no single platform controls the score — the same principle behind FICO aggregating across multiple credit bureaus.
|
|
85
85
|
|
|
86
|
+
## Works Great With agent-recall
|
|
87
|
+
|
|
88
|
+
[agent-recall](https://github.com/Thezenmonster/agent-recall) gives your AI persistent memory across sessions. Pair it with AgentScore and your agent can check trust once, remember it forever:
|
|
89
|
+
|
|
90
|
+
1. Agent calls `check_agent_trust` → gets score from AgentScore
|
|
91
|
+
2. Agent calls `remember` → stores the result in local SQLite
|
|
92
|
+
3. Next session, agent calls `recall("trust EmberFoundry")` → instant, no network call
|
|
93
|
+
|
|
94
|
+
```json
|
|
95
|
+
{
|
|
96
|
+
"mcpServers": {
|
|
97
|
+
"agentscore": {
|
|
98
|
+
"command": "npx",
|
|
99
|
+
"args": ["-y", "@agentscore-xyz/mcp-server"]
|
|
100
|
+
},
|
|
101
|
+
"memory": {
|
|
102
|
+
"command": "npx",
|
|
103
|
+
"args": ["-y", "agent-recall"]
|
|
104
|
+
}
|
|
105
|
+
}
|
|
106
|
+
}
|
|
107
|
+
```
|
|
108
|
+
|
|
109
|
+
Two tools, clean separation. Trust scoring stays in the cloud, memory stays local.
|
|
110
|
+
|
|
86
111
|
## Links
|
|
87
112
|
|
|
88
113
|
- **Website:** https://agentscores.xyz
|
package/dist/resources.js
CHANGED
|
@@ -32,7 +32,7 @@ Data Sources:
|
|
|
32
32
|
1. Moltbook — Social reputation (karma, posts, followers, verification)
|
|
33
33
|
2. ERC-8004 — On-chain identity (Ethereum agent registry)
|
|
34
34
|
3. ClawTasks — Work history (task completions, success rate, earnings)
|
|
35
|
-
4.
|
|
35
|
+
4. Molt Market — Freelance gigs (completed gigs, client feedback)
|
|
36
36
|
|
|
37
37
|
Five Scoring Dimensions (20 points each):
|
|
38
38
|
1. Identity — Verified accounts, on-chain registration, profile completeness
|
package/package.json
CHANGED
|
@@ -1,6 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@agentscore-xyz/mcp-server",
|
|
3
|
-
"version": "1.1
|
|
3
|
+
"version": "1.2.1",
|
|
4
|
+
"mcpName": "io.github.thezenmonster/agentscore",
|
|
4
5
|
"description": "MCP server for AgentScore — trust scoring for AI agents. Check agent reputation before transacting. No API key, zero config.",
|
|
5
6
|
"type": "module",
|
|
6
7
|
"bin": {
|