AI & Machine Learning

valem.run

Manages Valem model definitions, allowing creation, inspection, and retrieval of model specifications and library functions.

1 endpoint27 known toolsFirst detected August 22, 2026Last detected August 22, 2026

ENDPOINT 1

https://valem.run/mcp

No auth detected

MCP server metadata

Name: valem
Version: 1.0.0

Capabilities

toolsresources.subscribelogging

Server instructions

Valem is a deterministic reactive computation runtime for structured JSON models. Use create_model to compile a declarative ModelSpec (schema + derivations + constraints + effects), then mutate base fields — derived fields recompute automatically and constraints are enforced. Read merged state with get_state, trace any value with explain, and change the model in place with evolve_spec. State is in-memory for this session. This server is in remote_with_browser mode: call pair_browser first to get a verification link + confirmation code for the developer to approve in their browser; model operations fail until that pairing completes. Once paired, create_model/mutate/evolve_spec/get_state/explain all drive the SAME live session the browser has open, so the developer's own entered data is visible to get_state/explain, and an evolve_spec pushes the browser to re-render automatically — no copy-paste. Before evolve_spec, prefer dry_run(evolvedSpec, currentInputs) to preview whether the change would strand any of the developer's entered data; the server also rejects a stranding evolution with an error as a backstop.

Known tools 27

list_models

List the ids of all currently registered Valem models (alphabetical).

Inferred read-only

create_model

Create a new model from a declarative ModelSpec.

Potential side effects

get_model_info

Get summary info for a model: id, version, and derivation/meta/constraint/effect counts.

Inferred read-only

get_spec

Get the full stored ModelSpec JSON for a model.

Inferred read-only

get_library

List the JSONata functions and values a model's library exports — what an expression in this model may call, with signature, arity and originating layer.

Inferred read-only

get_state

Get a model's merged state (base fields plus all computed derived fields).

Inferred read-only

get_field

Get the value of a single field by its JSON Path address (e.

Inferred read-only

mutate

Apply field mutations to a model and run the reactive pipeline (derivations recompute, constraints enforce, effects dispatch).

Inferred read-only

patch_model

Apply an RFC 6902 JSON Patch document to a model and run the reactive pipeline.

Inferred read-only

get_effective_schema

Get the effective JSON Schema for a field: the static schema overlaid with LIVE meta-derived constraints (current min/max/required/…).

Inferred read-only

snapshot

Capture an immutable point-in-time snapshot of a model's state (base document + derived/meta caches).

Inferred read-only

restore

Restore a model's state from a snapshot previously returned by 'snapshot' (pass it back verbatim as 'snapshot').

Inferred read-only

explain

Explain why a field is what it is: returns the recent derivation/constraint trace records for a path from the in-memory ring buffer (inputs, expression, result).

Inferred read-only

get_history

List the ISO-8601 timestamps of a model's committed mutations (most recent 100).

Inferred read-only

get_audit

Query a model's durable, append-only audit trail (newest-first): one record per committed reactive cycle (mutations, derivedUpdated, traces, flaggedConstraints, dispatchedEffects, source, sequence).

Inferred read-only

verify_audit

Verify the tamper-evidence hash chain of a model's durable audit trail.

Inferred read-only

upload_blob

Store binary content (base64-encoded in 'data') in the content-addressed blob store and get back a BlobRef {$blobId, $mediaType, $bytes} to embed in a model's binary field.

Inferred read-only

download_blob

Fetch a blob's bytes by id, base64-encoded in the result.

Inferred read-only

evolve_spec

Apply an incremental SpecEvolution diff to a model, preserving live state.

Inferred read-only

delete_model

Remove a model from the registry.

Potential side effects

get_view

Evaluate a model's embedded view definition against current state and return the resolved component tree.

Inferred read-only

get_domain_guidance

Get vetted instructions for the hard modelling shapes this domain involves (progressive tax/fee charges, per-period schedules, classification, date math, group-by, …).

Inferred read-only

validate_spec

Validate a ModelSpec WITHOUT creating it: returns a 'valid' flag plus structured findings (errors + warnings, each with a location and message).

Potential side effects

eval_expression

Evaluate a single JSONata expression against a sample input document and return the computed value, or the exact compile/eval error.

Potential side effects

test_spec

Run a spec's embedded test cases (or ad-hoc given->expect cases) through the real reactive pipeline in a throwaway runtime, returning pass/fail plus per-field failures (path, expected, actual).

Inferred read-only

dry_run

Compile a candidate ModelSpec in an ISOLATED throwaway runtime, apply optional sample mutations, and return the resulting merged state (base + derived) — WITHOUT registering it in the live registry.

Inferred read-only

pair_browser

Pair this MCP session with a browser tab on the hosted Valem sandbox so both drive the same live model session.

Inferred read-only

CONNECT 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.valem]
url = "https://valem.run/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "valem": {
      "type": "http",
      "url": "https://valem.run/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: valem
Remote MCP URL: https://valem.run/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": {
    "valem": {
      "url": "https://valem.run/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "valem": {
      "type": "http",
      "url": "https://valem.run/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "valem",
  "transport": "streamable-http",
  "url": "https://valem.run/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 valem.run was fetched 2026-08-26T01:08:41.470Z.

Trust status Neutral

valem.run is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.