Valem is a remote MCP server that gives an AI agent 27 tools, among them create_model, delete_model, download_blob. It answers at https://valem.run/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 24 October 2026, succeeded.
Valem - Deterministic reactive state models. Create your own calculators/forms with AI
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
create_model | Create a new model from a declarative ModelSpec. The spec carries the JSON schema plus derivations (computed fields), constraints (invariants), and optional effects. Returns the created id. Fails (isError) on an invalid spec. If the request Inputs: spec |
delete_model | Remove a model from the registry. Fails (isError) if the model does not exist. Inputs: id |
download_blob | Fetch a blob's bytes by id, base64-encoded in the result. Pass 'modelId' to fetch a blob referenced by a specific model (access-scoped); omit it for a direct store fetch. Large blobs may exceed the result-size limit — this channel suits sma Inputs: blobId, modelId |
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. Use this to preview the full reactive cas Inputs: spec, mutations |
eval_expression | Evaluate a single JSONata expression against a sample input document and return the computed value, or the exact compile/eval error. Write the expr exactly as in a derivation/constraint 'expr': bare dot-paths, no leading $ (e.g. "loan.amoun Inputs: expr, input, library, constants |
evolve_spec | Apply an incremental SpecEvolution diff to a model, preserving live state. Returns the new version. Fails (isError) if the evolved spec is invalid, if expectedVersion no longer matches, or if a schema change would strand existing state. Pre Inputs: id, evolution |
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). For a constraint use the synthetic path "$constraint:<id>". Trace records can Inputs: id, path, limit |
get_audit | Query a model's durable, append-only audit trail (newest-first): one record per committed reactive cycle (mutations, derivedUpdated, traces, flaggedConstraints, dispatchedEffects, source, sequence). This is the queryable superset of get_his Inputs: id, pathPrefix, from, to, limit |
get_domain_guidance | Get vetted instructions for the hard modelling shapes this domain involves (progressive tax/fee charges, per-period schedules, classification, date math, group-by, …). Read the model description in ANY language, pick the matching topic ids, Inputs: topics |
get_effective_schema | Get the effective JSON Schema for a field: the static schema overlaid with LIVE meta-derived constraints (current min/max/required/…). Check this BEFORE writing a value to learn what the reactive pipeline will accept, instead of discovering Inputs: id, path |
get_field | Get the value of a single field by its JSON Path address (e.g. "$.order.total"). Evaluates a LAZY derivation on demand. Inputs: id, path |
get_history | List the ISO-8601 timestamps of a model's committed mutations (most recent 100). Inputs: id |
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. Call it before writing an expression so you reuse the model's existing vocabulary inst Inputs: id |
get_model_info | Get summary info for a model: id, version, and derivation/meta/constraint/effect counts. Inputs: id |
get_spec | Get the full stored ModelSpec JSON for a model. Inputs: id |
get_state | Get a model's merged state (base fields plus all computed derived fields). On a large model this is the biggest context cost — narrow it: pass 'paths' to project only specific subtrees (canonical addresses, each spliced back into a pruned d Inputs: id, at, paths, depth |
get_view | Evaluate a model's embedded view definition against current state and return the resolved component tree. Pass an optional 'viewId' for a named view; omit for the default view. Inputs: id, viewId |
list_models | List the ids of all currently registered Valem models (alphabetical). |
mutate | Apply field mutations to a model and run the reactive pipeline (derivations recompute, constraints enforce, effects dispatch). 'mutations' is a flat map keyed by canonical JSON Path address, e.g. {"$.order.qty": 3}. A ROLLBACK constraint vi Inputs: id, mutations, includeTraces |
pair_browser | Pair this MCP session with a browser tab on the hosted Valem sandbox so both drive the same live model session. Mints a pairing on first call (or resumes an existing not-yet-approved one) and waits up to a minute for the developer to approv |
patch_model | Apply an RFC 6902 JSON Patch document to a model and run the reactive pipeline. Unlike 'mutate' (a flat address→value map), a patch expresses array insert/remove/move and test/copy ops, e.g. [{"op":"add","path":"/order/items/-","value":{... Inputs: id, patch, includeTraces |
restore | Restore a model's state from a snapshot previously returned by 'snapshot' (pass it back verbatim as 'snapshot'). Overwrites the model's current base state. The snapshot must be for the same model. Inputs: id, snapshot |
snapshot | Capture an immutable point-in-time snapshot of a model's state (base document + derived/meta caches). A natural safety step before a risky evolve_spec: keep the returned snapshot and, if the change goes wrong, hand it back to 'restore' to r Inputs: id |
test_spec | Run a spec's embedded test cases (or ad-hoc given->expect cases) through the real reactive pipeline in a throwaway runtime, returning pass/fail plus per-field failures (path, expected, actual). Use this to certify domain behavior before cre Inputs: spec, tests |
upload_blob | Store binary content (base64-encoded in 'data') in the content-addressed blob store and get back a BlobRef {$blobId, $mediaType, $bytes} to embed in a model's binary field. Storage is content-addressed (SHA-256), so uploading identical byte Inputs: data, mediaType |
validate_spec | Validate a ModelSpec WITHOUT creating it: returns a 'valid' flag plus structured findings (errors + warnings, each with a location and message). Use this to iterate on a draft — fix the reported errors, re-validate — before committing with Inputs: spec |
verify_audit | Verify the tamper-evidence hash chain of a model's durable audit trail. Returns {valid, recordsChecked, firstBrokenSequence, detail}; a false 'valid' points at the first altered/reordered/deleted record. (Embedded mode has no hash chain and Inputs: id |
Every block below points at https://valem.run/mcp. Pick your client and copy.
claude mcp add --transport http valem https://valem.run/mcp
{
"mcpServers": {
"valem": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://valem.run/mcp"]
}
}
}{
"mcpServers": {
"valem": {
"url": "https://valem.run/mcp"
}
}
}{
"servers": {
"valem": {
"type": "http",
"url": "https://valem.run/mcp"
}
}
}{
"context_servers": {
"valem": {
"url": "https://valem.run/mcp"
}
}
}{
"mcpServers": {
"valem": {
"serverUrl": "https://valem.run/mcp"
}
}
}{
"mcpServers": {
"valem": {
"url": "https://valem.run/mcp"
}
}
}name: Valem
version: 0.0.1
schema: v1
mcpServers:
- name: Valem
type: streamable-http
url: https://valem.run/mcp{
"mcpServers": {
"valem": {
"httpUrl": "https://valem.run/mcp"
}
}
}{
"mcpServers": {
"valem": {
"type": "http",
"url": "https://valem.run/mcp"
}
}
}{
"mcpServers": {
"valem": {
"url": "https://valem.run/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fvalem.run%2Fmcp&type=streamable_http&id=valem&name=Valem
It answered our last check on 24 October 2026 in 162 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
27, as returned by the server's own tools/list on 22 September 2026: create_model, delete_model, download_blob, dry_run, eval_expression, evolve_spec, explain, get_audit, and 19 more.
It answered our last check on 24 October 2026 in 162 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://valem.run/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.vlad-public-code. Endpoint host: valem.run. ARD identifier: urn:air:io.github.vlad-public-code:mcp:valem.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.