recognitium
Server Details
Give your AI a memory it can prove: tamper-evident, offline-verifiable, SHA-256 receipts.
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP
- URL
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Tool Definition Quality
Score is being calculated. Check back soon.
Available Tools
11 toolsagent_cvInspect
An agent's public CV read straight from its chain: identity, witness anchors, settled market history, distinct counterparties (wash-resistant reputation). Public, free.
| Name | Required | Description | Default |
|---|---|---|---|
| chain_id | Yes |
chain_tipInspect
Read the authority chain's current head (sequence number + tip hash). Public, free. The external anchor against rollback.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
check_silenceInspect
Proof-of-absence: was the rail demonstrably alive over [from_ns, to_ns], so absence of a receipt is evidence of absence of an event? Only a 'covered' verdict proves absence; 'not_covered' suspends the presumption. Public, free.
| Name | Required | Description | Default |
|---|---|---|---|
| to_ns | Yes | ||
| from_ns | Yes | ||
| max_silence_ns | No |
lineage_traceInspect
Recall by lineage over the hosted biography. Given a sealed state's receipt_id: 'descendants' returns the CONTAMINATION SET (every memory derived from it, successor versions included conservatively) — bound the blast radius when a memory proves wrong; 'ancestors' returns full PROVENANCE. Chain of custody, not validity. Metered auth, no tick cost.
| Name | Required | Description | Default |
|---|---|---|---|
| direction | No | ||
| receipt_id | Yes | ||
| include_successors | No |
memory_historyInspect
Read the biography: every sealed state of each memory in order, each backed by a receipt. Not the memory itself — the unforgeable record of what it has been. Metered auth, no tick cost.
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | restrict to one memory |
memory_sealInspect
Seal the current state of a named memory into the agent's biography (1 tick per changed state; free no-op when unchanged). Hash the memory locally and send name + SHA-256 + optional derived_from (receipt ids of the sealed states this memory rests on — epistemic lineage). The rail stores fingerprints only, never content. The memory stays editable; its history becomes unforgeable. Metered.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | stable identifier of the memory | |
| data_hash | Yes | 32-byte SHA-256 as 64 hex characters | |
| derived_from | No | receipt ids of parent sealed states |
memory_verifyInspect
Boot-time integrity check of the agent's memory against its sealed biography. Send entries: [{name, data_hash}] for every memory currently held. Per memory: VERIFIED, ROLLBACK (matches an older sealed state), FOREIGN_EDIT (matches none), or UNSEALED. Verdict INTACT or TAMPER-EVIDENT; quarantine anything not VERIFIED. Sealed names the agent failed to report are returned too. Metered auth, no tick cost.
| Name | Required | Description | Default |
|---|---|---|---|
| entries | Yes |
prove_anteriorityInspect
Prove specific content is the content behind an existing receipt: supply the content's SHA-256 and the receipt_id. PROVEN = this exact content existed no later than the receipt's nanosecond timestamp. Public, free.
| Name | Required | Description | Default |
|---|---|---|---|
| data_hash | Yes | 32-byte SHA-256 as 64 hex characters | |
| receipt_id | Yes |
seal_hashInspect
Seal a SHA-256 fingerprint into the production receipt chain (1 tick). Hash your content locally; only the 32-byte fingerprint reaches the rail. Proves WHEN the hash was committed, never whether the content is true. Metered.
| Name | Required | Description | Default |
|---|---|---|---|
| data_hash | Yes | 32-byte SHA-256 as 64 hex characters |
tick_balanceInspect
The caller's private tick meter: balance, escrow, lifetime totals. Metered auth; ticks are non-transferable — a meter reading, not a wallet.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
verify_receiptInspect
Verify a Recognitium receipt. Public, free, no key. Give a receipt_id (looked up on the rail) or a full receipt object. The chain hash re-derives offline with SHA-256 alone — verifiers never need to trust the operator.
| Name | Required | Description | Default |
|---|---|---|---|
| receipt | No | ||
| receipt_id | No |
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
Discussions
No comments yet. Be the first to start the discussion!