Koskamo

ENYAL MCP

Provides trust infrastructure for autonomous AI agents, enabling identity management, encrypted memory archival, provable history via cryptographic ledgers, zero-knowledge proofs, and knowledge graph extraction. Agents can archive decisions, generate proofs, and disclose records securely.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

ENYAL MCP logo, by Greenland AI LimitedVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-07Operated by Greenland AI Limited
You need:your own ENYAL key (eyl_…) as Authorization: Bearer
MCP endpoint (Streamable HTTP)
https://mcp.enyal.ai/mcp
Vendor documentation

What its tools do

9 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

9 of 9 have a description · 9 of 9 declare behavior hints · 9 of 9 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Passed Official MCP Registry namespace is tied to enyal.ai ·
  • Passed Endpoint is on the registry namespace domain ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Archive agent decisions and actions to a cryptographic ledger
  • Generate zero-knowledge proofs for archived records
  • Manage scoped API keys for agent identity and spending
  • Extract knowledge graphs from archived data

Source and maintenance

Vendor evidenceRegistry 0.1.2

Protocol and capabilities

Server
ENYAL by Greenland AI 0.1.3+5208f45
MCP protocol negotiated in check
2025-11-25
Tools
9 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  },
  "experimental": {}
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

ENYAL by Greenland AI — identity, OAuth & cryptographic trust layer for AI agents. ENYAL encrypted-memory query. STRUCTURE tools (query_memory / get_entity / get_timeline / render) return graph STRUCTURE only (node_type, name_hash, relationships, chunk_ids, timestamps) — no content. CONTENT tools (query_memory_content / get_entity_content / get_timeline_content / get_node_content) return DECRYPTED content (names, summaries, evidence) and REQUIRE a memory:read:content-scoped token — a structure-only token calling them is rejected (403) by ENYAL. Same plan schema for both surfaces. Listing the tools (initialize, tools/list) needs no credential; every tool call needs your own ENYAL key (eyl_…) as Authorization: Bearer — this server holds none. Every tool is read-only.

Tools

9 advertised

query_memory
Advertised by the server during the last successful anonymous check.
Advertised read-only

Execute a structured query plan over your encrypted knowledge graph. Returns STRUCTURE ONLY (node_type, name_hash, relationships, chunk_ids, timestamps) — never content. Plan schema: { "entity_filters": [{"node_type": <type>} | {"name_hash": <sha256-hex>}], "edge_filters": [{"relationship": <rel>, "direction": "out"|"in"|"both"}], "temporal_bounds":{"valid_from_after": <ISO8601>, "valid_to_before": <ISO8601>}, "limit": <int <= 200>, "include_neighbours_depth": <0-5> } node_type in {entity, concept, decision, person, organisation, event, source, synthesis}. relationship in {references, contradicts, supports, supersedes, caused_by, related_to, part_of, informed_by, led_to, verifies}. Account scope is enforced server-side; it cannot be set from the plan.

query_memory input schema
{
  "type": "object",
  "title": "query_memoryArguments",
  "required": [
    "plan"
  ],
  "properties": {
    "plan": {
      "type": "object",
      "title": "Plan",
      "description": "The structured query plan (a JSON object): entity_filters [{node_type} | {name_hash}], edge_filters [{relationship, direction out|in|both}], temporal_bounds {valid_from_after, valid_to_before} (ISO 8601), limit (<= 200), include_neighbours_depth (0-5). The schema and the allowed node_type / relationship values are in this tool's description.",
      "additionalProperties": true
    },
    "include_chunks": {
      "type": "boolean",
      "title": "Include Chunks",
      "default": false,
      "description": "Also return the chunk ids behind each node. Default false."
    }
  }
}
query_memory annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
get_entity
Advertised by the server during the last successful anonymous check.
Advertised read-only

Get one entity's STRUCTURE by name_hash (SHA-256 of the normalised name). No content.

get_entity input schema
{
  "type": "object",
  "title": "get_entityArguments",
  "properties": {
    "node_id": {
      "type": "string",
      "title": "Node Id",
      "default": "",
      "description": "Accepted for compatibility but NOT used yet: the lookup is by name_hash only."
    },
    "name_hash": {
      "type": "string",
      "title": "Name Hash",
      "default": "",
      "description": "SHA-256 hex of the entity's normalised name. Send it: without it the plan has no entity filter."
    }
  }
}
get_entity annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
get_timeline
Advertised by the server during the last successful anonymous check.
Advertised read-only

Temporally-ordered STRUCTURE view, optionally filtered by node_type and an ISO8601 date range. No content.

get_timeline input schema
{
  "type": "object",
  "title": "get_timelineArguments",
  "properties": {
    "node_type": {
      "type": "string",
      "title": "Node Type",
      "default": "",
      "description": "Only nodes of this type: entity, concept, decision, person, organisation, event, source or synthesis. Empty = all."
    },
    "valid_to_before": {
      "type": "string",
      "title": "Valid To Before",
      "default": "",
      "description": "Only nodes valid to before this time (ISO 8601). Empty = no upper bound."
    },
    "valid_from_after": {
      "type": "string",
      "title": "Valid From After",
      "default": "",
      "description": "Only nodes valid from after this time (ISO 8601). Empty = no lower bound."
    }
  }
}
get_timeline annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
render
Advertised by the server during the last successful anonymous check.
Advertised read-only

Render a structured query as a STRUCTURE-ONLY result set (β = structure; identical shape to query_memory). Reserved for richer rendering when content access (γ) lands.

render input schema
{
  "type": "object",
  "title": "renderArguments",
  "required": [
    "plan"
  ],
  "properties": {
    "plan": {
      "type": "object",
      "title": "Plan",
      "description": "The structured query plan (a JSON object): entity_filters [{node_type} | {name_hash}], edge_filters [{relationship, direction out|in|both}], temporal_bounds {valid_from_after, valid_to_before} (ISO 8601), limit (<= 200), include_neighbours_depth (0-5). The schema and the allowed node_type / relationship values are in this tool's description.",
      "additionalProperties": true
    }
  }
}
render annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
verify_chunk
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Look up one identifier in ENYAL's PUBLIC verification index (relays GET /api/v1/verify/lookup/{id}; no decryption). ENYAL's answer is returned unchanged: `found`, and for a chunk or proof its `anchor_status` with `bsv_tx_id`; for a txid, `chain_status`. `degraded:true` means a source could not be checked (inconclusive, not an absence). ENYAL's route needs no key; calling it through this server still needs your eyl_ bearer, like every tool call. An id that is not a UUID or hex is refused (invalid_id) and nothing is sent.

verify_chunk input schema
{
  "type": "object",
  "title": "verify_chunkArguments",
  "required": [
    "identifier"
  ],
  "properties": {
    "identifier": {
      "type": "string",
      "title": "Identifier",
      "description": "The id to look up: a chunk, proof or transfer id (UUID), or a BSV transaction id (hex), 8-64 characters."
    }
  }
}
verify_chunk annotations
{
  "readOnlyHint": true,
  "openWorldHint": true,
  "idempotentHint": true,
  "destructiveHint": false
}
query_memory_content
Advertised by the server during the last successful anonymous check.
Advertised read-only

Execute a structured query plan and return DECRYPTED memory CONTENT (node names, summaries, properties; edge evidence + endpoint names) alongside structure. SAME plan schema as query_memory. REQUIRES a memory:read:content-scoped token — a structure-only token is rejected (403) by ENYAL. Account scope is enforced server-side; it cannot be set from the plan.

query_memory_content input schema
{
  "type": "object",
  "title": "query_memory_contentArguments",
  "required": [
    "plan"
  ],
  "properties": {
    "plan": {
      "type": "object",
      "title": "Plan",
      "description": "The structured query plan (a JSON object): entity_filters [{node_type} | {name_hash}], edge_filters [{relationship, direction out|in|both}], temporal_bounds {valid_from_after, valid_to_before} (ISO 8601), limit (<= 200), include_neighbours_depth (0-5). The schema and the allowed node_type / relationship values are in this tool's description.",
      "additionalProperties": true
    },
    "include_chunks": {
      "type": "boolean",
      "title": "Include Chunks",
      "default": false,
      "description": "Also return the chunk ids behind each node. Default false."
    }
  }
}
query_memory_content annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
get_entity_content
Advertised by the server during the last successful anonymous check.
Advertised read-only

Get one entity's DECRYPTED content by name_hash (SHA-256 of the normalised name). Content scope required (403 otherwise).

get_entity_content input schema
{
  "type": "object",
  "title": "get_entity_contentArguments",
  "properties": {
    "node_id": {
      "type": "string",
      "title": "Node Id",
      "default": "",
      "description": "Accepted for compatibility but NOT used yet: the lookup is by name_hash only."
    },
    "name_hash": {
      "type": "string",
      "title": "Name Hash",
      "default": "",
      "description": "SHA-256 hex of the entity's normalised name. Send it: without it the plan has no entity filter."
    }
  }
}
get_entity_content annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
get_timeline_content
Advertised by the server during the last successful anonymous check.
Advertised read-only

Temporally-ordered DECRYPTED content view, optionally filtered by node_type + an ISO8601 date range. Same plan schema as get_timeline. Content scope required (403 otherwise).

get_timeline_content input schema
{
  "type": "object",
  "title": "get_timeline_contentArguments",
  "properties": {
    "node_type": {
      "type": "string",
      "title": "Node Type",
      "default": "",
      "description": "Only nodes of this type: entity, concept, decision, person, organisation, event, source or synthesis. Empty = all."
    },
    "valid_to_before": {
      "type": "string",
      "title": "Valid To Before",
      "default": "",
      "description": "Only nodes valid to before this time (ISO 8601). Empty = no upper bound."
    },
    "valid_from_after": {
      "type": "string",
      "title": "Valid From After",
      "default": "",
      "description": "Only nodes valid from after this time (ISO 8601). Empty = no lower bound."
    }
  }
}
get_timeline_content annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
get_node_content
Advertised by the server during the last successful anonymous check.
Advertised read-only

Get a node's DECRYPTED content by name_hash PLUS its connected nodes' content (neighbour depth, default 1; 0–5). Same plan schema as the structure tools. Content scope required (403).

get_node_content input schema
{
  "type": "object",
  "title": "get_node_contentArguments",
  "properties": {
    "name_hash": {
      "type": "string",
      "title": "Name Hash",
      "default": "",
      "description": "SHA-256 hex of the entity's normalised name. Send it: without it the plan has no entity filter."
    },
    "include_neighbours_depth": {
      "type": "integer",
      "title": "Include Neighbours Depth",
      "default": 1,
      "description": "How many hops of connected nodes to include, 0-5 (clamped). Default 1."
    }
  }
}
get_node_content annotations
{
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (2 of 2 answered).

  1. 2026-11-07: 1 of 1 checks answered
  2. 2026-11-09: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
905 ms
95th percentile latency
905 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 905 ms · metadata changed · 9 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http enyal-mcp https://mcp.enyal.ai/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add enyal-mcp --url https://mcp.enyal.ai/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable enyal-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "enyal-mcp": {
      "url": "https://mcp.enyal.ai/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "enyal-mcp": {
      "type": "streamableHttp",
      "url": "https://mcp.enyal.ai/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start enyal-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "enyal-mcp": {
      "type": "http",
      "url": "https://mcp.enyal.ai/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http enyal-mcp https://mcp.enyal.ai/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://mcp.enyal.ai/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "enyal-mcp": {
      "serverUrl": "https://mcp.enyal.ai/mcp"
    }
  }
}

Let your agent find its tools

Find servers like ENYAL MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Do you run ENYAL MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing