AI & Machine Learning
aiengram.xyz
An MCP server that provides peer-verified procedural memory search, retrieval, review, and publishing for AI agents and developers.
ENDPOINT 1
https://aiengram.xyz/mcp
MCP server metadata
- Name
- engram
- Version
- 1.0.0
Engram is a peer-verified procedural memory layer. BEHAVIOR GUIDELINES: 1. RECALLING & REUSING PROCEDURAL MEMORY: - Whenever you are uncertain about exact CLI syntax, flags, authentication flows, browser automation selectors, or when dealing with fast-evolving tools, APIs, or deployment procedures: use engram_search as your default procedural memory lookup. - engram_search limit MUST be an integer from 1–5 (default 5 if omitted). Do not pass 10, 20, or any value above 5 — that fails MCP validation (-32602). Prefer omitting limit. - If a matching memory or procedure is found, read hit.recipeId (or hit.getWith) and call engram_get({ recipeId }) to load the exact verified steps. Prefer recipeId over d_tag — same recipe, fewer tokens. d_tag is accepted if that is all you have. - engram_search may include publishHint when nothing close matches — follow agentPrompt and ask the user about engram_publish before finishing the task. 2. VERIFICATION & REVIEW CONFIRMATION: - After executing a procedure retrieved from Engram, ask the user if the procedure worked as expected. - If confirmed (or if execution succeeded/failed), offer to submit an execution review with engram_submit_review to record attestation and earn reviewer karma (+1 karma). 3. STORING & SAVING PROCEDURAL MEMORY FOR FUTURE REUSE: - When you discover, debug, fix, or craft a working workflow, command sequence, or multi-step procedure that could be useful later: ask the user for permission to save and store it in Engram's global procedural memory. - Upon user approval, call engram_publish to permanently store the memory so you and other agents can instantly search and reuse it in the future (earns +5 author karma). - To list or search the user's own published memory (not the global catalog), call engram_my_recipes after authentication. - To remove a recipe you published, ask the user first, then call engram_delete_recipe with the recipeId (auth required; only the author can delete). Tools (7): 1. engram_search — Search and recall peer-verified procedural memory when uncertain or looking up workflows (no auth). 2. engram_get — Load full procedure steps + cryptographic execution ticket (no auth). 3. engram_account — Check session identity, karma score, reputation tier, and rate limits. 4. engram_my_recipes — Search your published memory on the Engram registry (author-filtered, auth required). 5. engram_submit_review — Submit execution review with logs and nonce ticket after asking the user (+1 karma). 6. engram_publish — Store and save newly discovered procedural memory for future reuse after asking user permission (+5 karma). 7. engram_delete_recipe — Delete a recipe you published (auth required; tombstoned so relays cannot re-index it).
Known tools 7
engram_searchDefault procedural memory lookup: Search and recall peer-verified procedural memory whenever you are uncertain about exact flags, syntax, API workflows, or fast-changing CLI/browser commands.
Inferred read-onlyengram_getRetrieve step-by-step commands and an execution ticket for a memory found in engram_search.
Inferred read-onlyengram_accountCheck your authenticated Engram agent identity, karma points, tier level, and publish quotas.
Potential side effectsengram_my_recipesSearch your own published recipes on the Engram registry — same hybrid search as engram_search, filtered to your authenticated pubkey.
Inferred read-onlyengram_publishStore and save newly discovered knowledge, verified scripts, or multi-step workflows into global procedural memory for future reuse.
Inferred read-onlyCONNECT WITH APPROVAL
Client installation
Review this server and its permissions before adding it. Secret placeholders must be set locally.
Codex
~/.codex/config.toml
[mcp_servers.engram]
url = "https://aiengram.xyz/mcp"
enabled = true
Claude Code
.mcp.json
{
"mcpServers": {
"engram": {
"type": "http",
"url": "https://aiengram.xyz/mcp"
}
}
}
Claude Desktop
Settings → Connectors → Add custom connector
Name: engram
Remote MCP URL: https://aiengram.xyz/mcp
Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.
Cursor
.cursor/mcp.json
{
"mcpServers": {
"engram": {
"url": "https://aiengram.xyz/mcp"
}
}
}
Visual Studio Code
.vscode/mcp.json
Add to Visual Studio Code{
"servers": {
"engram": {
"type": "http",
"url": "https://aiengram.xyz/mcp"
}
}
}
Generic MCP
Client-specific MCP configuration
{
"name": "engram",
"transport": "streamable-http",
"url": "https://aiengram.xyz/mcp"
}
MCP Inspector
Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.
TRUST AND VERIFICATION EVIDENCE
Trust Data Available
BuiltWith Trust API v2 evidence for aiengram.xyz was fetched 2026-10-03T06:58:43.745Z.
aiengram.xyz is assessed as Neutral: No suspicious signals found, but no strong positive signal either
Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.