MCP server exposing Credda's verifiable, bias-free trust layer to AI agents: check a counterparty's Credda trust before transacting, verify a credential they present to you, and mint your own to present back. Wraps existing public /verify endpoints; no sc
Drift inferred · capture-to-capture
tool count over time
tools
-
get_api_health
Readiness of the API this server reads from. No arguments.
-
get_investigation
One run: the reported issue, ranked hypotheses, any patches (unified diff, files changed, rationale) and any verification runs over them.
-
get_latest_resolution
The newest record for one investigation, or {"resolution": null} when it has produced none.
-
get_repository
One repository by id: name, clone source, default branch. Resolves the repositoryId every other row carries.
-
get_resolution
The whole record: reproduction and its captured failure signature, root cause, fix, verification signals, regression protection before/after, confidence and its named gaps.
-
get_validation
One validation, its environment and change impact, and the counts of checks, findings and evidence.
-
list_investigation_events
The run's timeline, cursor-paged with since / nextSince / hasMore. Debug events omitted unless includeDebug.
-
list_investigation_evidence
The observations a conclusion rests on: type, phase, strength, summary, artifact pointer.
-
list_investigations
The investigation queue: state, outcome, duration, event and evidence counts. Filter by repository, signal, state, outcome.
-
list_repositories
The repositories in your organisation. Start here to get an id.
-
list_repository_learnings
What Credda has learned about one repository, anchored to a file or symbol, with an observation count and an ordinal weight.
-
list_resolutions
Resolution records: what was reported, whether it reproduced, the verification verdict, regression status, and the confidence class with its notEstablished gaps.
-
list_validation_checks
The executed plan, in sequence. baseStatus is the load-bearing field.
-
list_validation_events
The validation's timeline, cursor-paged with since / nextSince / hasMore. Debug events omitted unless includeDebug.
-
list_validation_evidence
The evidence behind a validation's checks, filterable by type.
-
list_validation_findings
Severity, confidence, expected vs observed behaviour, reproduction, affected area, likely source. Narrow with severity and status.
-
list_validations
Validation runs over a change: state, outcome, commits compared, environment status.
code files: 11
filesystem 4
- fs (weak) Credda-io-credda-mcp-129bbb2/src/routeSurface.test.ts :39
import { readFileSync } from 'node:fs'; - fs (weak) Credda-io-credda-mcp-129bbb2/src/serverJson.test.ts :20
import { readFileSync } from 'node:fs'; - fs Credda-io-credda-mcp-129bbb2/src/version.ts :20
import { readFileSync } from 'node:fs'; - fs (weak) Credda-io-credda-mcp-129bbb2/src/writeSurface.test.ts :41
import { readFileSync } from 'node:fs';
network 3
- net (weak) Credda-io-credda-mcp-129bbb2/examples/try-the-server.mjs :22
import { createServer } from 'node:http'; - net Credda-io-credda-mcp-129bbb2/src/apiClient.ts :68
const doFetch = options.fetchImpl ?? ((...args: Parameters<typeof fetch>) => fetch(...args)); - net (weak) Credda-io-credda-mcp-129bbb2/src/writeSurface.test.ts :295
expect(source('tools.ts')).not.toContain('fetch(');
secrets 1
- secrets Credda-io-credda-mcp-129bbb2/src/index.ts :23
apiKey: process.env.CREDDA_API_KEY,
install hooks 1
- prepublishOnly Credda-io-credda-mcp-129bbb2/package.json :29
npm run check
declared dependencies 6
- @modelcontextprotocol/sdk@^1.30.0
- zod@^3.25.76
- @types/node@^20.14.2
- tsx@^4.23.1
- typescript@^5.4.5
- vitest@^3.2.7