Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Ricursor

REMOTE · API.RICURSOR.COM

Long-term, rotatable project memory and pre-write checks for AI coding agents.

Available components

68 Trust /100

Last scanned (18 hours ago)

Scores higher than 52% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Memory and Knowledge

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security71
Transport & Reachability100
Schema Quality & AI Usability56
  • AI-judged instruction clarity (fair).Partial
  • Tool/resource definitions use about 848 tokens (~70/item across 12 items; 12 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management20
  • Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage80
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 39% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 12 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (12)

  • TLS certificate
  • Authorization
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (1)

These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • HTTPS in Endpoint SecurityHTTPS enforcement could not be verified: the plaintext port answered with HTTP 401, which proves neither a plaintext path nor enforcement.

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Nov 26 0
    • Stability: unverified → 0.03 ▲ functional
  • 15 Nov 26 65

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://api.ricursor.com/v1/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=ricursor.com CN=WE1,O=Google Trust Services,C=US 21 Oct 2026 19 Jan 2027 ECDSA 256 ECDSA-SHA256 e1736f5d8ad372b2136804e618a3558f
SANs: ricursor.com, api.ricursor.com, *.api.ricursor.com
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of api.ricursor.com. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
com. DS published 19718 13 Verified
ricursor.com. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication Challenged, unverified

The endpoint asked for a token, but we could not retrieve and validate the RFC 9728 metadata that tells a client how to obtain one.

Result Challenged, unverified
Enforced On tool calls
HTTP status 200
Header Value
x-content-type-options nosniff
referrer-policy no-referrer

Protected resource metadata

Retrieved No
Problem No resource metadata

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://api.ricursor.com/v1/mcp Verified 200
http (plaintext) http://api.ricursor.com/v1/mcp Inconclusive 401
MCP tools · 12 exposed · ~796 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
ricursor_action_check ~117

Metadata-only decision for a JS/TS write or delete. Returns allow or block (with reasons to fix) plus a one-use receipt. Never send source.

NameTypeReqDescription
action_idstringyesUnique per proposed action, 8-80 characters.
baseline_hash–yes–
dependenciesarray––
expected_versioninteger––
kindstringyes–
metadataobject––
pathstringyes–
projectstringyes–
result_hashstring––

No output schema declared.

No examples provided.

ricursor_action_consume ~65

Atomically consumes a receipt immediately before the broker executes. Fails if anything changed.

NameTypeReqDescription
action_idstringyesUnique per proposed action, 8-80 characters.
baseline_hash–yes–
receiptstringyes–
result_hash–yes–

No output schema declared.

No examples provided.

ricursor_action_group_check ~70

Metadata-only decision for up to 20 related JS/TS writes/deletes judged on their combined end state (moves, renames).

NameTypeReqDescription
actionsarrayyes–
group_idstringyesUnique per proposed action, 8-80 characters.
projectstringyes–

No output schema declared.

No examples provided.

ricursor_action_group_consume ~49

All-or-nothing consumption before the broker writes the group.

NameTypeReqDescription
group_idstringyesUnique per proposed action, 8-80 characters.
receiptstringyes–

No output schema declared.

No examples provided.

ricursor_check ~77

Stop on block or errors. Checks tracked versions, exports and accepted import boundaries; never writes code.

NameTypeReqDescription
dependenciesarrayyes–
expected_versionintegeryes–
hashstringyes–
metadataobjectyes–
pathstringyes–
projectstringyesProject name inside the workspace.

No output schema declared.

No examples provided.

ricursor_context ~97

The verified corrections and recent file changes an agent must respect before it writes code.

NameTypeReqDescription
limitinteger––
projectstring–Project name inside the workspace.
sincestring–Previous cursor for this same key, project and task; returns changed rules and removed IDs.
taskstring–Task to retrieve relevant rules for.
workspacestring–Ignored: the key already selects its workspace.

No output schema declared.

No examples provided.

ricursor_correct ~81

After Ricursor blocks a check, save the one-sentence lesson so every agent on this project gets it. Only accepted for your own blocked action from the last 24 hours.

NameTypeReqDescription
action_idstringyesaction_id or group_id of the blocked check.
projectstringyesProject name inside the workspace.
rulestringyes–

No output schema declared.

No examples provided.

ricursor_handoff ~61

Save structured task IDs and versioned rule decisions; never include prompts or source.

NameTypeReqDescription
expected_versionintegeryes–
projectstringyesProject name inside the workspace.
stateobjectyes–
task_idstringyes–

No output schema declared.

No examples provided.

ricursor_ledger ~35

Read scoped metadata and rule versions before switching models. Observe only.

NameTypeReqDescription
projectstringyesProject name inside the workspace.

No output schema declared.

No examples provided.

ricursor_report ~85

Record what an agent spent (usage) and what it changed (state).

NameTypeReqDescription
projectstring–Project name inside the workspace.
request_idstringyesUnique ID per logical report; reuse unchanged when retrying.
stateobject––
usageobject––
workspacestring–Ignored: the key already selects its workspace.

No output schema declared.

No examples provided.

ricursor_snapshot ~42

Sync locally extracted JS/TS structural metadata only; never transmit source.

NameTypeReqDescription
filesarrayyes–
projectstringyesProject name inside the workspace.

No output schema declared.

No examples provided.

ricursor_workspaces ~17

The workspace this key can reach.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

Install

How do I install the Ricursor MCP server?

Ricursor is a hosted endpoint at https://api.ricursor.com/v1/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · api.ricursor.com

# add to Claude Code
claude mcp add --transport http com-ricursor-ricursor 'https://api.ricursor.com/v1/mcp'
Common questions

What is the Ricursor MCP server?

Ricursor is an MCP server listed in the public MCP registry as com.ricursor/ricursor. Long-term, rotatable project memory and pre-write checks for AI coding agents. This page covers its hosted endpoint (https://api.ricursor.com/v1/mcp).

Is the Ricursor MCP server safe to use?

Ricursor scores 68 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Ricursor MCP server expose?

Ricursor exposes 12 tools: ricursor_action_check, ricursor_action_consume, ricursor_action_group_check, ricursor_action_group_consume, ricursor_correct, and 7 more. Their descriptions and schemas cost roughly 796 tokens of context every time the server is loaded.

Does the Ricursor MCP server require authentication?

Yes. Ricursor asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

Is the Ricursor MCP server still maintained?

Ricursor is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the Ricursor MCP server?

VerifyMCP ran 12 checks on Ricursor, covering TLS certificate, Authorization, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about Ricursor: HTTPS. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.