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.

io.github.cronus42/ibc-mcp

REMOTE · RELOADINGCALC.COM

Physics interior-ballistics solver: solves, ladders, trajectory, lookups. Published error rates.

+3 this week 78 Trust /100

Last scanned (21 hours ago)

Scores higher than 72% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Health and Science

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 Security89
Transport & Reachability100
Schema Quality & AI Usability71
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 2402 tokens (~266/item across 9 items; 6 tools + 3 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management30
  • Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage91
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 73% 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 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
  • Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
What we tested

Checks we ran (13)

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

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.

  • 20 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 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.

  • 17 Nov 26 0
    • Tool “generate_load_ladder” rewrote its description, which is the text the model reads security
    • Tool “solve_internal_ballistics” rewrote its description, which is the text the model reads security
  • 16 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.

  • 14 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.

  • 13 Nov 26 0
    • Tool “solve_internal_ballistics” rewrote its description, which is the text the model reads security
    • Stability: unverified → 0.03 ▲ functional
  • 12 Nov 26 74

    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://reloadingcalc.com/mcp

TLS valid

Negotiated TLS 1.2 with TLS_ECDHE_RSA_WITH_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=reloadingcalc.com CN=Amazon RSA 2048 M04,O=Amazon,C=US 4 Oct 2026 19 Apr 2027 RSA 2048 SHA256-RSA 449f35808b2d603be936b04cb4a33f0
SANs: reloadingcalc.com, www.reloadingcalc.com
CN=Amazon RSA 2048 M04,O=Amazon,C=US (CA) CN=Amazon Root CA 1,O=Amazon,C=US 23 Aug 2022 23 Aug 2030 RSA 2048 SHA256-RSA 773124f2a952e3ed18a58bdb85d1bc0ce5f27
CN=Amazon Root CA 1,O=Amazon,C=US (CA) CN=Starfield Services Root Certificate Authority - G2,O=Starfield Technologies\, Inc.,L=Scottsdale,ST=Arizona,C=US 25 May 2015 31 Dec 2037 RSA 2048 SHA256-RSA 67f944a2a27cdf3fac2ae2b01f908eeb9c4c6

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of reloadingcalc.com. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
com. DS published 19718 13 Verified
reloadingcalc.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

WWW-Authenticate challenge Bearer realm="ibc-mcp"

Bearer realm="ibc-mcp"
Header Value
strict-transport-security max-age=63072000; includeSubDomains
x-content-type-options nosniff
x-frame-options DENY
referrer-policy strict-origin-when-cross-origin

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://reloadingcalc.com/mcp Verified 200
http (plaintext) http://reloadingcalc.com/mcp HTTPS enforced 301 https://reloadingcalc.com:443/mcp
MCP tools · 6 exposed · ~2,116 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
check_component_compatibility ~132

Check whether a cartridge+powder pair RESOLVES in the served database and whether the published-reference corpus contains a row for the pair (nearest-bullet membership — the same membership that decides a ladder's basis). Answers membership and canonical identity ONLY; it never serves the corpus row's numbers. Identity + published dimensional metadata only — NOT load data (rights-class discipline): no charge/velocity/pressure values are served by this tool.

NameTypeReqDescription
bullet_grnumber–Bullet weight in grains (optional; enables corpus-membership answer)
cartridgestringyes–
powderstringyes–

No output schema declared.

No examples provided.

generate_load_ladder ~526

PREFERRED for load development: generate a work-up ladder (>=5 rungs required — coarser requests are refused LADDER_TOO_COARSE, never silently interpolated) from the published-reference or charge-only bookends down, with per-rung trajectory nodes and the full safety envelope. Requires an API key or subscriber token — anonymous callers are refused pre-compute. Returns the SAME envelope as POST /v1/ladder. SAFETY (verbatim policy): Returns modeled pressure and velocity from a physics solver, plus a safety envelope. This is NOT published load data. Always present the envelope, warnings, and disclaimer to the user; never state a single charge weight as a recommendation. Pressure fields (p_max_bar, p_max_psi, saami_max_bar) are modeled compliance-vs-SAAMI-ceiling indicators on the model's CUP-equivalent scale, while pressure_percent_saami is reported piezo-equivalent: the percent equals p_max_bar x 1.2783 / saami_max_bar, so it is NOT peak / ceiling as served. The factor compensates a measured model under-drive on transducer anchors; the pure CUP-to-piezo convention component is bounded near 4-8%, and the remainder is genuine under-drive retained so an over-max load cannot read safe. Not measured proof pressures and not accuracy-validated numbers: the validation corpus is velocity-only. Treat them as position relative to the ceiling, with real-world spread unknown. not_for_loading_decisions_without_published_data: this result is a model output. Do not work up a load from it alone — cross-check against published data for your exact components before loading.

NameTypeReqDescription
barrel_len_innumberyesBarrel length in inches
bulletstringyesProjectile display name or projectile.csv id
caliberstringyesCartridge name or caliber.csv id
cartridge_oal_in––Cartridge overall length in inches (default: caliber max OAL)
charge_gr––Current charge (enables sensitivity + next-rung marker)
firearm_type––Revolver cylinder-gap override: 'auto' (default), 'revolver', or 'not_revolver' (rifle/pistol)
n_rungsinteger–Number of ladder rungs (3–10, default 7)
powderstringyesPropellant name or propellant.csv id
powder_temp_c––Powder temperature in °C (optional; -29..+49 validated band)
primer––Primer identity — accepted for forward compatibility

No output schema declared.

No examples provided.

get_cartridge_spec ~117

Look up ONE cartridge in the served component database (census: mode != 'hidden' AND geloescht == 0) by name, CIP name, alternate name, or id — returns the published dimensional spec (pmax_bar, case volume, bore/case dimensions, max OAL). Identity + published dimensional metadata only — NOT load data (rights-class discipline): no charge/velocity/pressure values are served by this tool.

NameTypeReqDescription
cartridgestringyesCartridge name, CIP name, alternate name, or numeric id

No output schema declared.

No examples provided.

list_powders ~87

List propellants in the served database (optionally filtered by manufacturer substring), with the GRT attributes the solver uses (Ba, Qex). Identity + published dimensional metadata only — NOT load data (rights-class discipline): no charge/velocity/pressure values are served by this tool.

NameTypeReqDescription
manufacturerstring–Optional manufacturer substring filter (e.g. 'Hodgdon')

No output schema declared.

No examples provided.

solve_internal_ballistics ~672

Solve one internal-ballistics point: modeled velocity/energy/pressure for an exact cartridge+bullet+powder+charge specification, wrapped in the non-removable safety envelope (charge range, closed-enum warnings, assumptions). Returns the SAME envelope as POST /v1/solve. Measured accuracy: velocity averages about 7.5% error against 30,327 published loads; the pressure a user sees displayed reads 7.38% low against printed CUP figures and 0.91% low against printed psi figures at the median, so verdicts are relative — start low and work up. For load DEVELOPMENT prefer generate_load_ladder (a work-up ladder with per-rung nodes). SAFETY (verbatim policy): Returns modeled pressure and velocity from a physics solver, plus a safety envelope. This is NOT published load data. Always present the envelope, warnings, and disclaimer to the user; never state a single charge weight as a recommendation. Pressure fields (p_max_bar, p_max_psi, saami_max_bar) are modeled compliance-vs-SAAMI-ceiling indicators on the model's CUP-equivalent scale, while pressure_percent_saami is reported piezo-equivalent: the percent equals p_max_bar x 1.2783 / saami_max_bar, so it is NOT peak / ceiling as served. The factor compensates a measured model under-drive on transducer anchors; the pure CUP-to-piezo convention component is bounded near 4-8%, and the remainder is genuine under-drive retained so an over-max load cannot read safe. Not measured proof pressures and not accuracy-validated numbers: the validation corpus is velocity-only. Treat them as position relative to the ceiling, with real-world spread unknown. not_for_loading_decisions_without_published_data: this result is a model output. Do not work up a load from it alone — cross-check against published data for your exact components before loading.

NameTypeReqDescription
barrel_len_innumberyesBarrel length in inches
bulletstringyesProjectile display name ('Mfr Product (W gr)') or projectile.csv id
caliberstringyesCartridge name or caliber.csv id
cartridge_oal_in––Cartridge overall length in inches (default: caliber max OAL)
charge_grnumberyesPowder charge in grains (sanity bounds 0.1..200)
firearm_type––Revolver cylinder-gap override: 'auto' (default, engine detects from caliber name), 'revolver', or 'not_revolver' (rifle/pistol)
powderstringyesPropellant name ('Alliant Blue Dot') or propellant.csv id
powder_temp_c––Powder temperature in °C (optional; -29..+49 validated band, clamped outside). None = ambient (default).
primer––Primer identity — accepted for forward compatibility; the engine does not model primers yet
weight_gr––Bullet weight override in grains (optional). For cast bullets: same mold, different alloy, different weight (a LEE C358-158-SWC can drop 137 gr in pewter/tin vs 158 gr catalog nominal). None = catalo…

No output schema declared.

No examples provided.

trajectory ~582

Trajectory / drop table: point-mass (3-DOF) exterior solve fed by the modeled muzzle velocity for an exact cartridge+bullet+powder+charge spec (or an explicit muzzle_velocity_fps override). Returns range rows (drop, velocity, energy, windage) plus the model assumptions. Beta keys get the table to 300 yd (the same PREFIX the web free tier gets); subscriber keys get the full table. No pressure figures on this surface. SAFETY (verbatim policy): Returns modeled pressure and velocity from a physics solver, plus a safety envelope. This is NOT published load data. Always present the envelope, warnings, and disclaimer to the user; never state a single charge weight as a recommendation. Pressure fields (p_max_bar, p_max_psi, pressure_percent_saami, saami_max_bar) are modeled compliance-vs-SAAMI-ceiling indicators, not measured proof pressures and not accuracy-validated numbers: the validation corpus is velocity-only. Treat them as position relative to the ceiling, with real-world spread unknown. not_for_loading_decisions_without_published_data: this result is a model output. Do not work up a load from it alone — cross-check against published data for your exact components before loading.

NameTypeReqDescription
barrel_len_innumberyesBarrel length in inches
bc_lb_in2––Ballistic coefficient override; default = catalog g7bc (else g1bc) for the bullet
bulletstringyesProjectile display name ('Mfr Product (W gr)') or projectile.csv id
caliberstringyesCartridge name or caliber.csv id
cartridge_oal_in–––
charge_grnumberyesPowder charge in grains
drag_function––Drag standard of `bc_lb_in2`; default G1 for an override, otherwise whichever catalog BC was used
firearm_type–––
max_range_ydnumber––
muzzle_velocity_fps––Override; default = the engine's v_max_fps for this load
powderstringyesPropellant name or propellant.csv id
powder_temp_c–––
pressure_hpanumber––
primer–––
sight_height_innumber––
step_ydnumber––
temp_cnumber––
weight_gr––Bullet weight override in grains (optional). For cast bullets: same mold, different alloy, different weight (a LEE C358-158-SWC can drop 137 gr in pewter/tin vs 158 gr catalog nominal). None = catalo…
wind_mphnumber–Full-value crosswind, left -> right
zero_range_ydnumber––

No output schema declared.

No examples provided.

Install

How do I install the io.github.cronus42/ibc-mcp server?

io.github.cronus42/ibc-mcp is a hosted endpoint at https://reloadingcalc.com/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 · reloadingcalc.com

# add to Claude Code
claude mcp add --transport http cronus42-ibc-mcp 'https://reloadingcalc.com/mcp'
Common questions

What is the io.github.cronus42/ibc-mcp server?

io.github.cronus42/ibc-mcp is listed in the public MCP registry as io.github.cronus42/ibc-mcp. Physics interior-ballistics solver: solves, ladders, trajectory, lookups. Published error rates. This page covers its hosted endpoint (https://reloadingcalc.com/mcp).

Is the io.github.cronus42/ibc-mcp server safe to use?

io.github.cronus42/ibc-mcp scores 78 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 io.github.cronus42/ibc-mcp server expose?

io.github.cronus42/ibc-mcp exposes 6 tools: solve_internal_ballistics, generate_load_ladder, trajectory, get_cartridge_spec, list_powders, check_component_compatibility. Their descriptions and schemas cost roughly 2,116 tokens of context every time the server is loaded.

Does the io.github.cronus42/ibc-mcp server require authentication?

Yes. io.github.cronus42/ibc-mcp 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 io.github.cronus42/ibc-mcp server still maintained?

io.github.cronus42/ibc-mcp 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 io.github.cronus42/ibc-mcp server?

VerifyMCP ran 13 checks on io.github.cronus42/ibc-mcp, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. 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.