emem, the verifiable memory protocol for the physical world

Compose a memory_token citation handle

emem_memory_token

Read-onlyIdempotent

Mint a citation handle, emem:fact:<cell64>:<fact_cid> (or :<state_cid>), that any agent or LLM resolves to the byte-identical signed object. The antidote to referential drift on the value side: hand this one string to another agent instead of re-describing the fact. Validates both components are non-empty and free of the : separator. Memory algebra: the cite operation (https://emem.dev/docs/model.html).

When to use: Call when you want one rebindable string to cite a place plus an attested fact across messages, threads, agents or tools. Pair it with emem_echo_verify before you publish the value. FOR MANY FACTS USE emem_memory_bundle INSTEAD, and this is measured rather than stylistic: a token is 83 to 84 characters and 51 LLM tokens while the value it points at averages 11 characters and 5.4, so N tokens cost about 9.5x the context of pasting the N numbers and hit the window sooner. A bundle is 38 characters at any N up to 256 and resolves in one round trip: it wins from N=1 against tokens and from N=5 against the plain values. Individual tokens are for citing ONE fact you must verify later.

Example arguments: {"cell":"defi.zb493.xoso.zcb6a","fact_cid":"cxjiu7l54ujzrpnekp24n4534yojpue4mprddbvevnqtti3lh5bq"}

Input Schema

TableJSON Schema

Name	Required	Description
`band`	No	Optional band key. When set, the minted citation carries the band's tamper-provenance block (class, deterministic, tamper_evidence, trust_rank) so the receiving agent sees the trust class without a resolve round-trip.
`cell`	Yes	cell64, neither component may contain `:`.
`fact_cid`	Yes	52-char base32-nopad-lowercase content-id of the fact (full 32-byte blake3).
`observed_on`	No	The fact's source capture date (YYYY-MM-DD) as `/v1/recall` reports it in `sources[].captured_at`. Supplied together with `band` it additionally mints the self-describing `descriptor_token`. A wrong date forges nothing: resolve binds the date to the signed fact and answers 409 on a mismatch.

Output Schema

TableJSON Schema

Name	Required	Description
`cell`	Yes
`docs`	No
`grammar`	No	The token grammar, so the form can be parsed rather than pattern-matched.
`fact_cid`	Yes
`cell_token`	No	The address alone, when you mean the place rather than an observation of it.
`memory_token`	Yes	The citation to paste: emem:fact:<cell64>:<fact_cid>. Copy it verbatim; a hand-assembled token that is one character wrong still reads as a citation and resolves to nothing.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedAug 12, 2026

addedInput schema / properties / observed_on

Added value: +{
+  "description": "The fact's source capture date (YYYY-MM-DD) as `/v1/recall` reports it in `sources[].captured_at`. Supplied together with `band` it additionally mints the self-describing `descriptor_token`. A wrong date forges nothing: resolve binds the date to the signed fact and answers 409 on a mismatch.",
+  "type": "string"
+}

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "cell": {
+      "type": "string"
+    },
+    "cell_token": {
+      "description": "The address alone, when you mean the place rather than an observation of it.",
+      "type": "string"
+    },
+    "docs": {
+      "type": "string"
+    },
+    "fact_cid": {
+      "type": "string"
+    },
+    "grammar": {
+      "description": "The token grammar, so the form can be parsed rather than pattern-matched.",
+      "type": "string"
+    },
+    "memory_token": {
+      "description": "The citation to paste: emem:fact:<cell64>:<fact_cid>. Copy it verbatim; a hand-assembled token that is one character wrong still reads as a citation and resolves to nothing.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "memory_token",
+    "cell",
+    "fact_cid"
+  ],
+  "type": "object"
+}

Changed1 schema field changedJul 28, 2026

changedInput schema / properties / cell / description

Previous value: -"cell64 — neither component may contain `:`."New value: +"cell64, neither component may contain `:`."

Changed2 schema fields changedJul 11, 2026

addedInput schema / properties / band

Added value: +{
+  "description": "Optional band key. When set, the minted citation carries the band's tamper-provenance block (class, deterministic, tamper_evidence, trust_rank) so the receiving agent sees the trust class without a resolve round-trip.",
+  "type": "string"
+}

changedInput schema / properties / fact_cid / description

Previous value: -"26-char base32-nopad-lowercase content-id of the fact."New value: +"52-char base32-nopad-lowercase content-id of the fact (full 32-byte blake3)."

AddedMay 31, 2026
RemovedMay 28, 2026

Changed3 schema fields changedMay 23, 2026

addedInput schema / properties / cell / maxLength
```
Added value: +23
```
addedInput schema / properties / cell / minLength
```
Added value: +19
```

addedInput schema / properties / cell / pattern

Added value: +"^(?:(?:[bcdfghjklmnpqrstvwxyz][aeiouAEIOU]){2}|z[0-9a-f]{4})(?:\\.(?:(?:[bcdfghjklmnpqrstvwxyz][aeiouAEIOU]){2}|z[0-9a-f]{4})){3}$"

AddedMay 16, 2026

TDQS

A4.6/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: it details validation logic (non-empty, no `:` separator), the resolution semantics (byte-identical signed object), and error behavior (409 on date mismatch). While it doesn't explicitly restate read-only status, it complements annotations with operational details, earning a 4.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded in the first sentence, followed by usage guidance, a detailed comparison with bundles, and an example. The cost analysis paragraph is longer than strictly necessary but is well-structured and provides decision-relevant data. No superfluous fluff; every sentence serves a function. Slightly long but appropriately organized for an agent to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present (context signal says it has one), the description does not need to explain return values. It covers the input purpose, when to use, trade-offs vs. alternatives, validation constraints, and gives a concrete example. For an agent deciding whether to call this tool and how to invoke it correctly, nothing essential is missing. Complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% (all 4 parameters have descriptions). The description adds an illustrative example with real-looking values and explains the validation rule that both components must be free of `:`, which is not fully captured in the schema (the pattern for `cell` exists, but `fact_cid` has no such constraint). This supplements the schema notations and provides meaning beyond the basic property descriptions, so a 4 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific output: it mints a citation handle in the exact format `emem:fact:<cell64>:<fact_cid>` (or `:<state_cid>`). It distinguishes itself from the sibling `emem_memory_bundle` by explicitly noting that individual tokens are for citing ONE fact, while bundles handle many facts. The verb 'Mint' and resource 'citation handle' are clear and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit when-to-use: 'Call when you want one rebindable string to cite a place plus an attested fact across messages, threads, agents or tools.' It also states when NOT to use it: 'FOR MANY FACTS USE emem_memory_bundle INSTEAD' with a quantitative comparison of token costs and context overhead. It even recommends pairing with `emem_echo_verify` before publishing. This is model-exemplary usage guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All emem, the verifiable memory protocol for the physical world tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.