Skip to main content
Glama

agent-trust-oracle

Server Details

Decay-weighted reputation + tamper-evident trust attestations for the agent economy.

Status
Healthy
Last Tested
Transport
Streamable HTTP
URL
Repository
jdhart81/viridis-agent-fleet
GitHub Stars
0
Server Listing
viridis-agent-fleet

Glama MCP Gateway

Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.

MCP client
Glama
MCP server

Full call logging

Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.

Tool access control

Enable or disable individual tools per connector, so you decide what your agents can and cannot do.

Managed credentials

Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.

Usage analytics

See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.

100% free. Your data is private.
Tool DescriptionsC

Average 2.9/5 across 6 of 6 tools scored. Lowest: 2.1/5.

Server CoherenceA
Disambiguation5/5

Each tool has a clearly distinct purpose: attest issues attestations, describe_agent provides self-description, history shows history and score, record_outcome records outcomes, score_agent retrieves scores, verify_attestation verifies attestations. No overlap in functionality.

Naming Consistency4/5

Names mostly follow verb_noun pattern (attest, describe_agent, record_outcome, score_agent, verify_attestation) with consistent lowercase underscores. 'history' is a slight noun-only deviation but still clear and predictable.

Tool Count5/5

6 tools is well-scoped for an agent trust oracle. Each tool addresses a necessary aspect: attestation, outcome recording, scoring, history, verification, and self-description. No extraneous or missing core operations.

Completeness5/5

The tool set covers the full lifecycle of trust management: creating attestations (attest), recording outcomes (record_outcome), querying scores and history (score_agent, history), verifying attestations (verify_attestation), and self-description (describe_agent). No obvious gaps for the stated purpose.

Available Tools

6 tools
attestInspect

Issue a tamper-evident (hash-chained) trust attestation for an agent.

ParametersJSON Schema
NameRequiredDescriptionDefault
claimNoreputation-snapshot
agent_idYes

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
describe_agentInspect

Fleet-standard self-description.

ParametersJSON Schema
NameRequiredDescriptionDefault

No parameters

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
historyInspect

Full outcome history + attestation count + current score for an agent.

ParametersJSON Schema
NameRequiredDescriptionDefault
agent_idYes

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
record_outcomeInspect

Record an interaction outcome for an agent. kind: success | delivered | dispute_won | failure | undelivered | dispute_lost | timeout | security_incident (security incidents carry a 3x penalty).

ParametersJSON Schema
NameRequiredDescriptionDefault
kindYes
noteNo
weightNo
agent_idYes
counterpartyNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
score_agentInspect

Get an agent's decay-weighted trust score in [0,1] and tier. Unknown agents get a neutral 0.5 prior — no blind trust, no unfair zero.

ParametersJSON Schema
NameRequiredDescriptionDefault
agent_idYes

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes
verify_attestationInspect

Verify a previously issued attestation by recomputing its hash.

ParametersJSON Schema
NameRequiredDescriptionDefault
agent_idYes
attestation_idYes

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

Discussions

No comments yet. Be the first to start the discussion!

Try in Browser

Your Connectors

Sign in to create a connector for this server.