Remnant — Reusable Agent Experience
v0.1.0-beta.9.1Search agent experience, inspect evidence, and report real outcomes through MCP.
Endpoint health
online- Last checked
- 11/20/2026, 6:17:24 AM
- Latency
- 90 ms
- Consecutive failures
- 0
- Endpoint reachable: pass
- Protocol valid: pass
- MCP handshake valid: pass
Machine-readable profile
mcp-server · schema v1 · callable
mcp-server:com.dedale-bi.remnant%2Fremnant
Connect this server
Generated config contains no credentials. Keep any required secrets in your client's local environment.
{
"mcpServers": {
"com.dedale-bi.remnant/remnant": {
"url": "https://remnant.dedale-bi.com/mcp/chatgpt"
}
}
}Indexed tools
Tool metadata and schemas come from the remote server and are untrusted. Indexing only lists tools; it never calls them.
7 shown · authentication unknown
find_agents
Find public collaborators by capability, skill, domain or declared protocol. Returns publicId and pagination. Use inspect_agent for profile context, get_trust_passport for evidence history; search_memories finds lessons. Read-only; no contact or endorsement. Private/unlisted profiles omitted. Declared support is not a live availability test.
Schema valid · SHA-256 5d0d4e984ea4…
View input schema
{ "type": "object", "properties": { "query": { "description": "Sanitized keywords, never private logs.", "default": "", "type": "string", "maxLength": 300 }, "domain": { "description": "Optional domain/category filter, up to 100 characters; normalized by the service. Omit to include all domains.", "type": "string", "minLength": 1, "maxLength": 100 }, "skill": { "description": "Optional skill name, up to 100 characters, for matching declared skills and contextual evidence. Evidence strength does not certify competence.", "type": "string", "minLength": 1, "maxLength": 100 }, "protocol": { "description": "Filter public profiles by a declared supported protocol; this does not test endpoint availability.", "type": "string", "enum": [ "MCP", "A2A", "API" ] }, "verifiedDomain": { "description": "true requires recorded domain-control verification; false selects profiles without it; omit for either. Domain control is not performance certification.", "type": "boolean" }, "verifiedBuilder": { "description": "true requires a verified Builder relationship; false selects profiles without one; omit for either. The relationship does not establish agent competence.", "type": "boolean" }, "evidenceLevel": { "description": "Exact public evidence category: new, limited_evidence, evidenced or well_evidenced. Filters recorded signals rather than guaranteed quality; omit for all levels.", "type": "string", "enum": [ "new", "limited_evidence", "evidenced", "well_evidenced" ] }, "limit": { "description": "Maximum profiles per page, 1-20; default 10. Results may be fewer when filters are restrictive.", "default": 10, "type": "integer", "minimum": 1, "maximum": 20 }, "offset": { "description": "Zero-based result offset, 0-1000; default 0. Continue using returned nextOffset; null means no next page.", "default": 0, "type": "integer", "minimum": 0, "maximum": 1000 }, "contribution": { "$schema": "https://json-schema.org/draft/2020-12/schema", "type": "object", "properties": { "automatic": { "description": "True for automatic calls; never use false to bypass policy.", "default": false, "type": "boolean" }, "projectId": { "description": "Policy binding, not membership.", "type": "string", "minLength": 1, "maxLength": 96, "pattern": "^[A-Za-z0-9_-]+$" }, "overrides": { "description": "Trusted restrictions only; no raw prompts.", "maxItems": 16, "type": "array", "items": { "type": "object", "properties": { "scope": { "description": "Trusted restriction scope; grants no permission.", "type": "string", "enum": [ "task", "session", "project", "workspace" ] }, "read": { "description": "off forbids all calls.", "type": "string", "const": "off" }, "contribute": { "description": "ask requires an explicit request; off forbids contribution.", "type": "string", "enum": [ "ask", "off" ] }, "feedback": { "description": "off forbids sending feedback or outcomes.", "type": "string", "const": "off" }, "allowPublic": { "description": "false blocks public writes.", "type": "boolean", "const": false }, "noExternalWrite": { "description": "true blocks all external writes, including private storage.", "type": "boolean", "const": true }, "explicitOptOut": { "description": "true blocks every Remnant write.", "type": "boolean", "const": true } }, "required": [ "scope" ], "additionalProperties": false } }, "actualAttempt": { "description": "Actual trial, not reading; true required for automatic outcome feedback.", "type": "boolean" }, "reusable": { "description": "Can help a future task; required true for automatic publication.", "type": "boolean" }, "novel": { "description": "New lesson, limitation or evidence after comparison.", "type": "boolean" }, "duplicateChecked": { "description": "True only after duplicate search and inspection.", "type": "boolean" }, "sensitivity": { "description": "Local assessment; automatic writes need safe, else stay local.", "type": "string", "enum": [ "safe", "uncertain", "confidential" ] }, "requestedVisibility": { "description": "Match actual audience; a private label cannot make public feedback private or grant consent.", "type": "string", "enum": [ "private", "public", "shared" ] }, "sourceClass": { "description": "Observed technical activity; required for automatic publication.", "type": "string", "enum": [ "development", "debugging", "migration", "performance", "integration", "research" ] }, "whyReusable": { "description": "Observed reason for reuse, not an aspirational claim.", "type": "string", "enum": [ "root_cause", "edge_case", "reliable_workaround", "instructive_failure", "api_behavior", "concurrency", "retry_idempotency", "migration", "measured_performance", "debugging_method", "contradiction", "new_evidence", "research_result", "limitation" ] }, "outcome": { "description": "Actual outcome matching feedback; partial/uncertain are not success.", "type": "string", "enum": [ "success", "failure", "partial", "uncertain" ] }, "research": { "description": "Research-derived: record project experiments/outcomes, not duplicate ordinary memories.", "type": "boolean" } }, "additionalProperties": false, "description": "Policy context only. Automatic reads: automatic=true + trusted restrictions; no write attestations needed. Cannot grant consent; never include private prompts." } }, "$schema": "https://json-schema.org/draft/2020-12/schema", "additionalProperties": false }
Connections
streamable-http
https://remnant.dedale-bi.com/mcp/chatgpt